Tong Zhang's Homepage

Publications

Selected papers from 2000 to present.

, "," , , (editors), , , , vol. , (), pp. , , . [doi] [code available] [long version]

@article{CRZ00,
  author = {Jane Cullum and Albert Ruehli and Tong Zhang},
  title = {A method for reduced-order modeling and simulation of large
    interconnect circuits and its application to PEEC models
    including retardation},
  journal = {IEEE Trans. Circ. Sys.},
  year = 2000,
  volume = 47,
  url = {http://tongzhang-ml.org/papers/cs00_modred.pdf},
  pages = {261--273}
}

@article{ZhOl01,
  author = {Tong Zhang and Frank J. Oles},
  title = {Text Categorization based on regularized linear classification
       methods},
  journal = {Information Retrieval},
  year = 2001,
  volume = 4,
  url = {http://tongzhang-ml.org/papers/ir01_textcat.pdf},
  pages = {5--31}
}

@article{Zhang00-dualth,
  author = {Tong Zhang},
  title = {On the dual formulation of regularized linear systems},
  journal = {Machine Learning},
  volume = 46,
  pages = {91--129},
  url = {http://tongzhang-ml.org/papers/ml02_dual.pdf},
  year = 2002
}

@article{ZhTo02,
  author = {Tong Zhang and Carlo Tomasi},
  title = {On the Consistency of Instantaneous Rigid Motion Estimation},
  journal = {International Journal of Computer Vision},
  year = 2002,
  volume = 46,
  url = {http://tongzhang-ml.org/papers/ijcv02_motion.pdf},
  pages = {51--79}
}

@article{ZhGo01,
  author = {Tong Zhang and Gene H. Golub},
  title = {Rank-one approximation to high order tensors},
  journal = {SIAM Journal on Matrix Analysis and Applications},
  year = 2001,
  volume = 23,
  url = {http://tongzhang-ml.org/papers/siamax01_msvd.pdf},
  pages = {534--550}
}

@article{Zhang00-cover,
  author = {Tong Zhang},
  title = {Covering Number Bounds of Certain Regularized Linear 
    Function Classes},
  journal = {Journal of Machine Learning Research},
  year = 2002,
  volume = 2,
  url = {http://tongzhang-ml.org/papers/jmlr02_cover.pdf},
  pages = {527--550}
}

@article{ZDJ02,
  author = {Tong Zhang and Fred Damerau and David E. Johnson},
  title = {Text Chunking based on a Generalization of {W}innow},
  journal = {Journal of Machine Learning Research},
  year = 2002,
  volume = 2,
  url = {http://tongzhang-ml.org/papers/jmlr02_chunking.pdf},
  pages = {615--637}
}

@article{ZhIy01,
  author = {Tong Zhang and Vijay S. Iyengar},
  title = {Recommender Systems Using Linear Classifiers},
  journal = {Journal of Machine Learning Research},
  year = 2002,
  volume = 2,
  url = {http://tongzhang-ml.org/papers/jmlr02_cf.pdf},
  pages = {313--334}
}

@article{JOZG02,
  author = {D. E. Johnson and F. J. Oles and T. Zhang and T. Goetz},
  title = {A Decision-Tree-Based Symbolic Rule Induction System for 
Text Categorization},
  journal = {IBM Systems Journal},
  year = 2002,
  volume = 41,
  url = {http://tongzhang-ml.org/papers/ibmsys02_tree.pdf},
  pages = {428--437}
}

@article{CulZh02,
  author = {Jane Cullum and Tong Zhang},
  title = {Two-sided {A}rnoldi and non-symmetric {L}anczos Algorithms},
  journal = {SIAM Journal on Matrix Analysis and Applications},
  year = 2002,
  volume = 24,
  url = {http://tongzhang-ml.org/papers/siamax02_arnoldi.pdf},
  pages = {303--319}
}

@article{Zhang01-ker_greedy,
  author = {Tong Zhang},
  title = {Approximation Bounds for Some Sparse Kernel Regression Algorithms},
  journal = {Neural Computation},
  year = 2002,
  volume = 14,
  url = {http://tongzhang-ml.org/papers/nc02_greedy.pdf},
  pages = {3013--3042}
}

@article{Zhang01-consistency,
  author = {Tong Zhang},
  title = {Statistical Behavior and Consistency of Classification Methods based on Convex Risk Minimization},
  journal = {The Annals of Statistics},
  year = 2004,
  volume = 32,
  pages = {56--85},
  url = {http://tongzhang-ml.org/papers/aos04_consistency.pdf},
  note = {with discussion}
}

@article{Zhang01-greedy,
  author = {Tong Zhang},
  title = {Sequential Greedy Approximation for Certain Convex
  Optimization Problems},
  journal = {IEEE Transaction on Information Theory},
  year = 2003,
  volume = 49,
  url = {http://tongzhang-ml.org/papers/it03_greedy.pdf},
  pages = {682--691}
}

@article{Zhang02-loo,
  author = {Tong Zhang},
  title = {Leave-one-out Bounds for Kernel Methods},
  journal = {Neural Computation},
  year = 2003,
  volume = 15,
  url = {http://tongzhang-ml.org/papers/nc03_loo.pdf},
  pages = {1397--1437}
}

@article{FZWI03,
  author = {Fred J. Damerau and Tong Zhang and Sholom M. Weiss 
and Nitin Indurkhya},
  title = {Text Categorization for a Comprehensive Time-Dependent Benchmark},
  journal = {Information Processing \& Management},
  year = 2004,
  volume = 40,
  url = {http://tongzhang-ml.org/papers/ipm04-new_reuters.pdf},
  pages = {209-221}
}

@article{MeiZha03,
  author = {Ron Meir and Tong Zhang},
  title = {Generalization Error Bounds for {B}ayesian Mixture Algorithms},
  journal = {Journal of Machine Learning Research},
  year = 2003,
  volume = 4,
  url = {http://tongzhang-ml.org/papers/jmlr03-mixture.pdf},
  pages = {839--860}
}

@article{MaMeZh03,
  author = {Shie Mannor and Ron Meir and Tong Zhang},
  title = {Greedy Algorithms for Classification - Consistency,
                  Convergence Rates, and Adaptivity},
  journal = {Journal of Machine Learning Research},
  year = 2003,
  volume = 4,
  url = {http://tongzhang-ml.org/papers/jmlr03-boost.pdf},
  pages = {713--741}
}

@article{Zhang04-multi,
  author = {Tong Zhang},
  title = {Statistical Analysis of Some Multi-category Large Margin Classification Methods},
  journal = {Journal of Machine Learning Research},
  year = 2004,
  volume = 5,
  url = {http://tongzhang-ml.org/papers/jmlr04-multicat.pdf},
  pages = {1225--1251}
}

@article{ZhYu05,
  author = {Tong Zhang and Bin Yu},
  title = {Boosting with Early Stopping: Convergence and Consistency},
  journal = {The Annals of Statistics},
  year = 2005,
  volume = 33,
  url = {http://tongzhang-ml.org/papers/aos05-boost.pdf},
  pages = {1538--1579}
}

@article{Zhang05-nc,
  author = {Tong Zhang},
  title = {Learning Bounds for Kernel Regression using Effective Data 
Dimensionality},
  journal = {Neural Computation},
  year = 2005,
  volume = 17,
  url = {http://tongzhang-ml.org/papers/nc05-ker.pdf},
  pages = {2077--2098}
}

@article{Ando+Zhang05:semi,
  author = {Rie Kubota Ando and Tong Zhang},
  title = {A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data},
  journal = {Journal of Machine Learning Research},
  year = 2005,
  volume = 6,
  url = {http://tongzhang-ml.org/papers/jmlr05_semisup.pdf},
  pages = {1817--1853}
}

@article{Zhang06:dens,
  author = {Tong Zhang},
  title = {From $\epsilon$-entropy to {KL}-entropy: 
Analysis of Minimum Information Complexity Density Estimation},
  journal = {The Annals of Statistics},
  year = 2006,
  volume = 34,
  url = {http://tongzhang-ml.org/papers/aos06-dens.pdf},
  pages = {2180--2210}
}

@article{Zhang06:infoexp,
  author = {Tong Zhang},
  title = {Information Theoretical Upper and Lower Bounds for Statistical Estimation},
  journal = {IEEE Trans. Info. Theory},
  year = 2006,
  volume = 52,
  url = {http://tongzhang-ml.org/papers/it06-bound.pdf},
  pages = {1307--1321}
}

@article{JohnsonZhang07-jmlr,
  author = {Rie Johnson and Tong Zhang},
  title = {On the Effectiveness of {L}aplacian Normalization for Graph Semi-supervised Learning},
  journal = {Journal of Machine Learning Research},
  year = 2007,
  volume = 8,
  url = {http://tongzhang-ml.org/papers/jmlr07-graph.pdf},
  pages = {1489--1517}
}

@article{JohnsonZhang07-it,
  author = {Rie Johnson and Tong Zhang},
  title = {Graph-based Semi-supervised Learning and Spectral Kernel Design},
  journal = {IEEE Trans. Info. Theory},
  year = 2008,
  volume = 54,
  url = {http://tongzhang-ml.org/papers/it08-graph.pdf},
  pages = {275--288}
}

@article{TillmannZhang07,
  author = {Christoph Tillmann and Tong Zhang},
  title = {A Block Bigram Prediction Model for Statistical Machine Translation},
  journal = {ACM Transactions on Speech and Language Processing},
  year = 2007,
  url = {http://tongzhang-ml.org/papers/acm_slp07.pdf},
  volume = 4
}

@article{TillmannZhang08,
  author = {Christoph Tillmann and Tong Zhang},
  title = {An Online Relevant Set Algorithm for Statistical Machine Translation},
  journal = {IEEE Transactions on Audio, Speech, and Language processing},
  volume = 16,
  number = 7,
  pages = {1274--1286},
  url = {http://tongzhang-ml.org/papers/taslp08-mt.pdf},
  year = 2008
}

@article{CossockZhang08,
  author = {David Cossock and Tong Zhang},
  title = {Statistical Analysis of {B}ayes Optimal Subset Ranking},
  journal = {IEEE Transactions on Information Theory},
  year = 2008,
  volume = 54,
  number = 11,
  url = {http://tongzhang-ml.org/papers/it08-ranking.pdf},
  pages = {5140-5154}
}

@article{Zhang07-l1,
  author = {Tong Zhang},
  title = {Some sharp performance bounds for least squares regression with {$L_1$} regularization},
  journal = {Ann. Statist.},
  fjournal = {Annals of Statistics},
  year = {2009},
  volume = {37},
  number = {5A},
  pages = {2109-2144},
  issn = {0090-5364},
  doi = {10.1214/08-AOS659},
  url = {http://tongzhang-ml.org/papers/aos09-L1.pdf},
  arxiv = {0908.2869},
  sici = {0090-5364(2009)37:5A<2109:SSPBFL>2.0.CO;2-4}
}

@article{Zhang08-forward,
  author = {Tong Zhang},
  title = {On the Consistency of Feature Selection using Greedy Least Squares Regression},
  journal = {Journal of Machine Learning Research},
  year = {2009},
  volume = {10},
  number = {19},
  pages = {555-568},
  url = {http://jmlr.org/papers/v10/zhang09a.html}
}

@article{LanLiZha09,
  author = {John Langford and Lihong Li and Tong Zhang},
  title = {Sparse Online Learning via Truncated Gradient},
  journal = {Journal of Machine Learning Research},
  year = {2009},
  volume = {10},
  number = {28},
  pages = {777-801},
  url = {http://jmlr.org/papers/v10/langford09a.html}
}

@article{BFGJJRZ08,
  author = {Andrei Broder and Marcus Fontoura and Evgeniy Gabrilovich and 
Amruta Joshi and Vanja Josifovski and Lance Riedel and Tong Zhang},
  title = {Classifying Search Quries Using the Web as a Source of Knowledge},
  journal = {ACM Transactions on the Web},
  year = 2009,
  volume = 3,
  url = {http://tongzhang-ml.org/papers/tweb09-qclass.pdf},
  pages = {1--28}
}

@incollection{Zhang09-handbook,
  author = {Tong Zhang},
  booktitle = {Handbook of Natural Language Processing},
  title = {Fundamental Statistical Techniques},
  editor = {Nitin Indurkhya and Fred Damerau},
  publisher = {Chapman \& Hall/CRC},
  year = 2009,
  url = {http://www.crcpress.com/product/isbn/9781420085921},
  edition = {2nd}
}

@article{HuangZhang09,
  author = {Junzhou Huang and Tong Zhang},
  title = {The Benefit of Group Sparsity},
  journal = {Annals of Statistics},
  year = 2010,
  volume = 38,
  url = {http://tongzhang-ml.org/papers/aos10-group.pdf},
  pages = {1978--2004}
}

@article{zhang09-multistage,
  author = {Tong Zhang},
  title = {Analysis of Multi-stage Convex Relaxation for Sparse Regularization},
  journal = {Journal of Machine Learning Research},
  year = {2010},
  volume = {11},
  number = {35},
  pages = {1081-1107},
  codenote = {Multistage Convex Relaxation Method for Sparse Learing (R code)},
  coderef = {http://tongzhang-ml.org/code/muscor.zip},
  url = {http://jmlr.org/papers/v11/zhang10a.html}
}

@article{ShSrZh09,
  author = {Shai Shalev-Shwartz and Nathan Srebro and Tong Zhang},
  title = {Trading Accuracy for Sparsity in Optimization Problems with Sparsity Constraints},
  journal = {Siam Journal on Optimization},
  year = 2010,
  volume = 20,
  url = {http://tongzhang-ml.org/papers/siopt10-sparsity.pdf},
  pages = {2807--2832}
}

@article{CaiZhaWan10,
  author = {Cai, Zhipeng AND Zhang, Tong AND Wan, Xiu-Feng},
  journal = {PLoS Comput Biol},
  publisher = {Public Library of Science},
  title = {A Computational Framework for Influenza Antigenic Cartography},
  year = 2010,
  month = 10,
  volume = 6,
  url = {http://dx.doi.org/10.1371%2Fjournal.pcbi.1000949},
  pages = {e1000949},
  number = 10,
  doi = {10.1371/journal.pcbi.1000949}
}

@article{Zhang08-foba,
  author = {Tong Zhang},
  title = {Adaptive Forward-Backward Greedy Algorithm for Learning Sparse Representations},
  journal = {IEEE Transactions on Information Theory},
  year = 2011,
  volume = 57,
  url = {http://tongzhang-ml.org/papers/it11-foba.pdf},
  codenote = {Forward Backward Greey Algorithm for Sparse Learning (R code)},
  coderef = {http://tongzhang-ml.org/code/foba.zip},
  pages = {4689--4708}
}

@article{LLZLWZ11,
  author = {Li, Wenyuan AND Liu, Chun-Chi AND Zhang, Tong AND Li, Haifeng AND Waterman, Michael S. AND Zhou, Xianghong Jasmine},
  journal = {PLoS Comput Biol},
  publisher = {Public Library of Science},
  title = {Integrative Analysis of Many Weighted Co-Expression Networks Using Tensor Computation},
  year = 2011,
  month = 06,
  volume = 7,
  url = {http://dx.doi.org/10.1371\%2Fjournal.pcbi.1001106},
  pages = {e1001106},
  number = 6,
  doi = {10.1371/journal.pcbi.1001106}
}

@article{Zhang11-greedy_rip,
  author = {Tong Zhang},
  title = {Sparse Recovery with Orthogonal Matching Pursuit under {RIP}},
  journal = {IEEE Transactions on Information Theory},
  year = 2011,
  volume = 57,
  url = {https://arxiv.org/pdf/1005.2249.pdf},
  pages = {6215 - 6221}
}

@article{CaZhWa11-cartopt,
  author = {Zhipeng Cai and Tong Zhang and Xiu-Feng Wan},
  title = {Concepts and applications for influenza antigenic cartography},
  journal = {Influenza and Other Respiratory Viruses},
  year = 2011,
  volume = 5,
  number = {Suppl. 1},
  url = {http://dx.doi.org/10.1016/j.jmb.2012.05.011},
  pages = {204--207}
}

@article{HsKaTz11-robust,
  author = {Daniel Hsu and Sham Kakade and Tong Zhang},
  title = {Robust Matrix Decomposition with Sparse Corruptions},
  journal = {IEEE Transactions on Information Theory},
  year = 2011,
  volume = 57,
  url = {http://tongzhang-ml.org/papers/it11-sparselowrank.pdf},
  pages = {7221--7234}
}

@article{HuangZhang09:structured_sparsity,
  author = {Junzhou Huang and Tong Zhang and Dimitris Metaxas},
  title = {Learning with Structured Sparsity},
  journal = {Journal of Machine Learning Research},
  year = {2011},
  volume = {12},
  number = {103},
  pages = {3371-3412},
  url = {http://jmlr.org/papers/v12/huang11b.html}
}

@article{HsKaZh12,
  author = {Daniel Hsu and Sham M. Kakade and Tong Zhang},
  title = { A Spectral Algorithm for Learning Hidden Markov Models},
  journal = {Journal of Computer and System Sciences},
  year = 2012,
  volume = 78,
  number = 5,
  url = {https://arxiv.org/abs/0811.4413},
  pages = {1460-1480}
}

@article{HsKaZh12-matrix-tail,
  author = {Daniel Hsu and Sham M. Kakade and Tong Zhang},
  title = {Tail inequalities for sums of random matrices that depend on the intrinsic dimension},
  journal = {Electronic Communications in Probability},
  year = 2012,
  volume = 17,
  url = {http://ecp.ejpecp.org/article/view/1869},
  pages = {article 14}
}

@article{Zhang12-multistage-fs,
  author = {Tong Zhang},
  title = {Multistage Convex Relaxation for Feature Selection},
  journal = {Bernoulli},
  year = 2013,
  volume = 19,
  url = {http://arxiv.org/abs/1106.0565},
  pages = {2277--2293}
}

@article{ZhZh12-concave,
  author = {Cunhui Zhang and Tong Zhang},
  title = {A General Theory of Concave Regularization for High Dimensional Sparse Estimation Problems},
  journal = {Statistical Science},
  year = 2012,
  volume = 27,
  url = {http://arxiv.org/abs/1108.4988},
  pages = {576--593}
}

@article{DaPhZh12,
  author = {Dong Dai and Philippe Rigollet and Tong Zhang},
  title = {Deviation Optimal Learning using Greedy {Q}-aggregation},
  journal = {Annals of Statistics},
  year = 2012,
  volume = 40,
  url = {http://arxiv.org/abs/1203.2507},
  pages = {1878--1905}
}

@article{CDYZLBWW12,
  author = {Zhipeng Cai and Mariette F Ducatez and Jialiang Yang and Tong Zhang and Li-Ping Long and Adrianus C.  Boon and Richard J.  Webby and Xiu-Feng Wan},
  title = {Identifying antigenicity associated sites in highly pathogenic {H}5{N}1 influenza virus hemagglutinin by using sparse learning},
  journal = {Journal of Molecular Biology},
  url = {http://dx.doi.org/10.1016/j.jmb.2012.05.011},
  year = 2012
}

@article{HsKaZh12-subGaussian-tail,
  author = {Daniel Hsu and Sham M. Kakade and Tong Zhang},
  title = {A tail inequality for quadratic forms of subgaussian random vectors},
  journal = {Electronic Communications in Probability},
  year = 2012,
  volume = 17,
  url = {https://projecteuclid.org/journals/electronic-communications-in-probability/volume-17/issue-none/A-tail-inequality-for-quadratic-forms-of-subgaussian-randomvectors/10.1214/ECP.v17-2079.full},
  pages = {article 52}
}

@article{ShalevZhang13,
  author = {Shai Shalev-Shwartz and Tong Zhang},
  title = {Stochastic Dual Coordinate Ascent Methods for Regularized Loss Minimization},
  journal = {Journal of Machine Learning Research},
  volume = 14,
  pages = {567--599},
  url = {https://arxiv.org/abs/1209.1873},
  year = 2013
}

@article{YuanZhang13-speig,
  author = {Xiaotong Yuan and Tong Zhang},
  title = {Truncated Power Method for Sparse Eigenvalue Problems},
  journal = {Journal of Machine Learning Research},
  volume = 14,
  pages = {899--925},
  url = {https://arxiv.org/abs/1112.2679},
  codenote = {Truncated Power Method for sparse PCA (in matlab)},
  coderef = {http://tongzhang-ml.org/code/TPower.zip},
  year = 2013
}

@article{XiaoZhang13-homo,
  author = {Xiao, Lin and Zhang, Tong},
  title = {A Proximal-Gradient Homotopy Method for the Sparse Least-Squares Problem},
  journal = {SIAM Journal on Optimization},
  volume = 23,
  number = 2,
  pages = {1062-1091},
  year = 2013,
  doi = {10.1137/120869997},
  url = {http://arxiv.org/abs/1203.3002},
  eprint = {http://epubs.siam.org/doi/pdf/10.1137/120869997}
}

@article{YuZhWa13,
  author = {Xiao-Tong Yuan and Tong Zhang and Xiu-Feng Wan},
  title = {A Joint Matrix Completion and Filtering Model for Influenza Serological Data Integration},
  journal = {PLoS ONE},
  year = 2013,
  volume = 8,
  number = 7,
  pages = {e69842},
  doi = {10.1371/journal.pone.0069842}
}

@article{YuanZhang14-pggm,
  author = {Xiaotong Yuan and Tong Zhang},
  title = {Partial {G}aussian Graphical Model Estimation},
  journal = {IEEE Transactions on Information Theory},
  volume = 60,
  pages = {1673--1687},
  url = {http://arxiv.org/abs/1209.6419},
  year = 2014
}

@article{HsKaZh14,
  year = 2014,
  issn = {1615-3375},
  journal = {Foundations of Computational Mathematics},
  doi = {10.1007/s10208-014-9192-1},
  title = {Random Design Analysis of Ridge Regression},
  url = {http://dx.doi.org/10.1007/s10208-014-9192-1},
  publisher = {Springer US},
  author = {Hsu, Daniel and Kakade, Sham M. and Zhang, Tong},
  pages = {1-32},
  language = {English}
}

@article{DaRiXiZh14,
  author = {Dong Dai and Philippe Rigollet and Lucy Xia and Tong Zhang},
  title = {Aggregation of affine estimators},
  journal = {Electron. J. Statist.},
  fjournal = {Electronic Journal of Statistics},
  year = 2014,
  volume = 8,
  pages = {302-327},
  issn = {1935-7524},
  doi = {10.1214/14-EJS886},
  url = {https://arxiv.org/abs/1311.2799}
}

@article{JohnZha14-pami,
  author = {Rie Johnson and Tong Zhang},
  title = {Learning Nonlinear Functions Using Regularized Greedy Forest},
  journal = {PAMI},
  year = 2014,
  volume = 36,
  url = {https://arxiv.org/pdf/1109.0887.pdf},
  codenote = {RGF Method for Boosted Decision Trees (in C++ with python interface)},
  coderef = {https://github.com/RGF-team/rgf},
  pages = {942--954}
}

@article{WaLiZh2014-aos,
  author = {Zhaoran Wang and Han Liu and Tong Zhang},
  title = {Optimal computational and statistical rates of convergence for sparse nonconvex learning problems},
  journal = {Ann. Statist.},
  fjournal = {Annals of Statistics},
  year = 2014,
  volume = 42,
  number = 6,
  pages = {2164-2201},
  issn = {0090-5364},
  doi = {10.1214/14-AOS1238},
  url = {http://arxiv.org/abs/1306.4960}
}

@article{XiaZha14,
  author = {Lin Xiao and Tong Zhang},
  title = {A Proximal Stochastic Gradient Method with Progressive Variance Reduction},
  journal = {SIAM Journal on Optimization},
  year = 2014,
  volume = 24,
  url = {http://arxiv.org/abs/1403.4699},
  pages = {2057--2075}
}

@article{Shalev-Zhang14-accl,
  author = {Shai Shalev-Shwartz and Tong Zhang},
  title = {Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization},
  journal = {Mathematical Programming},
  year = 2016,
  volume = 155,
  url = {https://arxiv.org/abs/1309.2375},
  codenote = {Accelerated Prox-SDCA Method for large scale L1-L2 Regularized Linear Models (in C++)},
  coderef = {https://github.com/TongZhang-ML/sparseSDCA},
  pages = {105--145}
}

@article{SSSHZ15-jmlr,
  author = {Sivan Sabato and Shai Shalev-Shwartz and Nathan Srebro and Daniel Hsu and Tong Zhang},
  title = {Learning Sparse Low-Threshold Linear Classifiers},
  journal = {Journal of Machine Learning Research},
  year = 2015,
  volume = 16,
  url = {https://arxiv.org/abs/1212.3276},
  pages = {1275--1304}
}

@article{WZZ16-jmlr,
  author = {Shusen Wang and Zhihua Zhang and Tong Zhang},
  title = {Towards More Efficient {SPSD} Matrix Approximation and {CUR} Matrix Decomposition},
  journal = {Journal of Machine Learning Research},
  year = 2016,
  volume = 17,
  url = {https://arxiv.org/abs/1503.08395},
  pages = {1--49}
}

@article{SXWWZZZ17-tkde,
  author = {Jun Song and Jun Xiao and Fei Wu and Haishan Wu and Tong Zhang and Zhongfei Zhang and Wenwu Zhu},
  title = {Hierarchical Contextual Attention Recurrent Neural Network for Map Query Suggestion},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = 2017,
  doi = {10.1109/TKDE.2017.2700392}
}

@article{FLSZ17-aos,
  author = {Jianqing Fan and Han Liu and Qiang Sun and Tong Zhang},
  title = {I-LAMM for Sparse Learning: Simultaneous Control of Algorithmic Complexity and Statistical Error},
  journal = {Annals of Statistics},
  volume = 46,
  pages = {814-841},
  url = {https://arxiv.org/abs/1507.01037},
  year = 2018
}

@article{ZhLiZh18-aos,
  author = {Tuo Zhao and Han Liu and Tong Zhang},
  title = {Pathwise coordinate optimization for sparse learning: Algorithm and theory},
  journal = {Ann. Statist.},
  fjournal = {Annals of Statistics},
  year = 2018,
  volume = 46,
  number = 1,
  pages = {180-218},
  issn = {0090-5364},
  doi = {10.1214/17-AOS1547},
  url = {https://arxiv.org/abs/1412.7477}
}

@article{ZWXXZ17-jmlr,
  author = {Shun Zheng and Jialei Wang and Fen Xia and Wei Xu and Tong Zhang},
  title = {A General Distributed Dual Coordinate Optimization Framework for Regularized Loss Minimization},
  journal = {Journal of Machine Learning Research},
  year = {2017},
  volume = {18},
  number = {115},
  pages = {1-52},
  url = {http://jmlr.org/papers/v18/16-463.html}
}

@article{LWLZ17-mathprog,
  author = {Chris J. Li and Mengdi Wang and Han Liu and Tong Zhang},
  title = {Near-Optimal Stochastic Approximation for Online Principal Component Estimation},
  journal = {Mathematical Programming},
  pages = {75--97},
  volume = {167},
  url = {https://arxiv.org/abs/1603.05305},
  year = 2018
}

@article{YuanLiZhang18-jmlr,
  author = {Xiao-Tong Yuan and Ping Li and Tong Zhang},
  title = {Gradient Hard Thresholding Pursuit},
  journal = {Journal of Machine Learning Research},
  year = {2018},
  volume = {18},
  number = {166},
  pages = {1-43},
  url = {http://jmlr.org/papers/v18/14-415.html}
}

@article{DHYZ18-it,
  author = {Dong Dai and Lei Han and Ting Yang and Tong Zhang},
  journal = {IEEE Transactions on Information Theory},
  title = {Bayesian Model Averaging With Exponentiated Least Squares Loss},
  year = {2018},
  volume = {64},
  number = {5},
  pages = {3331-3345},
  url = {https://arxiv.org/abs/1408.1234},
  doi = {10.1109/TIT.2018.2805903}
}

@article{TACL18-tacl,
  author = {Tu, Zhaopeng  and Liu, Yang  and Shi, Shuming  and Zhang, Tong },
  title = {Learning to Remember Translation History with a Continuous Cache},
  journal = {Transactions of the Association for Computational Linguistics},
  volume = {6},
  year = {2018},
  issn = {2307-387X},
  url = {https://arxiv.org/abs/1711.09367},
  pages = {407--420}
}

@article{HLWZZW18-bioinfo,
  author = {Lei Han and Lei Li and Feng Wen and Lei Zhong and Tong Zhang and Xiu-Feng Wan},
  title = {Graph-Guided Multi-Task Sparse Learning Model: a Method for Identifying Antigenic Variants of Influenza A(H3N2) Virus},
  journal = {Bioinformatics},
  volume = 105,
  pages = {769--782},
  year = 2018,
  url = {https://doi.org/10.1093/bioinformatics/bty457}
}

@article{TWLZ18,
  author = {Kean Ming Tan and Zhaoran Wang and Han Liu and Tong Zhang},
  title = {Sparse Generalized Eigenvalue Problem: Optimal Statistical Rates via Truncated {R}ayleigh Flow},
  journal = {Journal of the Royal Statistical Society: Series B},
  volume = 80,
  pages = {1057--1086},
  url = {https://arxiv.org/abs/1604.08697},
  year = 2018
}

@article{TWZLC18,
  author = {Kean Ming Tan and Zhaoran Wang and Tong Zhang and Han Liu and R. Dennis Cook},
  title = {A Convex Formulation For High-Dimensional Sparse Sliced Inverse Regression},
  journal = {Biometrika},
  year = 2018,
  volume = 105,
  number = 4,
  url = {https://arxiv.org/abs/1809.06024},
  pages = {769--782}
}

@article{LSZLZW19,
  author = {Wenhan Luo and Peng Sun and Fangwei Zhong and Wei Liu and Tong Zhang and Yizhou Wang},
  title = {End-to-end Active Object Tracking and Its Real-world Deployment via Reinforcement Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  volume = 42,
  pages = {1317--1332},
  url = {https://arxiv.org/abs/1808.03405},
  year = 2020
}

@article{LCZLZ19,
  author = {Luo Luo and Cheng Chen and Zhihua Zhang and Wu-Jun Li and Tong Zhang},
  title = {Robust Frequent Directions with Application in Online Learning},
  journal = {Journal of Machine Learning Research},
  year = 2019,
  volume = 20,
  number = 45,
  pages = {1-41},
  url = {http://jmlr.org/papers/v20/17-773.html}
}

@article{WanZha19,
  author = {Jialei Wang and Tong Zhang},
  title = {Utilizing Second Order Information in Minibatch Stochastic Variance Reduced Proximal Iterations},
  journal = {Journal of Machine Learning Research},
  year = 2019,
  volume = 20,
  number = 42,
  pages = {1-56},
  url = {http://jmlr.org/papers/v20/17-594.html}
}

@article{GLJLZWZ19,
  author = {Jason Ge and Xingguo Li and Haoming Jiang and Han Liu and Tong Zhang and Mengdi Wang and Tuo Zhao},
  title = {Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python},
  journal = {Journal of Machine Learning Research},
  year = 2019,
  volume = 20,
  number = 44,
  pages = {1-5},
  url = {http://jmlr.org/papers/v20/17-722.html}
}

@article{TLZL19,
  author = {Kean Ming Tan and Junwei Lu and Tong Zhang and Han Liu},
  title = {Layer-Wise Learning Strategy for Nonparametric Tensor Product Smoothing Spline Regression and Graphical Models},
  journal = {Journal of Machine Learning Research},
  year = 2019,
  volume = 20,
  number = 119,
  pages = {1-38},
  url = {http://jmlr.org/papers/v20/17-525.html}
}

@article{CMSZ19-siopt,
  author = {Shixiang Chen and Shiqian Ma and Anthony Man-Cho So and Tong Zhang},
  title = {Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold},
  journal = {Siam Journal of Optimization},
  volume = 30,
  number = 1,
  pages = {210-239},
  url = {https://arxiv.org/abs/1811.00980},
  year = 2020
}

@article{WSZG20-ijcv,
  author = {Baoyuan Wu and Li Shen and Tong Zhang and Bernard Ghanem},
  title = {MAP Inference via L2-Sphere Linear Program Reformulation},
  journal = {International Journal of Computer Vision},
  url = {https://doi.org/10.1007/s11263-020-01313-2},
  year = 2020
}

@article{HTYZ20-aos,
  author = {Lei Han and Kean Ming Tan and Ting Yang and Tong Zhang},
  title = {Local uncertainty sampling for large-scale multiclass logistic regression},
  journal = {Ann. Statist.},
  fjournal = {Annals of Statistics},
  year = {2020},
  volume = {48},
  number = {3},
  pages = {1770-1788},
  issn = {0090-5364},
  doi = {10.1214/19-AOS1867},
  url = {https://arxiv.org/abs/1604.08098},
  sici = {0090-5364(2020)48:3<1770:LUSFLS>2.0.CO;2-6}
}

@article{TLZL20-biometrics,
  title = {Estimating and inferring the maximum degree of stimulus-locked time-varying brain connectivity networks},
  author = {Tan, Kean Ming and Lu, Junwei and Zhang, Tong and Liu, Han},
  journal = {Biometrics},
  volume = 77,
  number = 2,
  pages = {379--390},
  year = 2021,
  publisher = {Wiley Online Library},
  url = {https://arxiv.org/pdf/1905.11588},
  doi = {10.1111/biom.13297}
}

@article{JohZha20-cfggan,
  title = {A framework of composite functional gradient methods for generative adversarial models},
  author = {Johnson, Rie and Zhang, Tong},
  journal = {IEEE transactions on pattern analysis and machine intelligence},
  volume = 43,
  number = 1,
  pages = {17--32},
  year = 2019,
  publisher = {IEEE},
  doi = {10.1109/TPAMI.2019.2924428},
  url = {https://ieeexplore.ieee.org/document/8744312}
}

@article{ZYLZB-21,
  title = {Finite-sample analysis for decentralized batch multiagent reinforcement learning with networked agents},
  author = {Zhang, Kaiqing and Yang, Zhuoran and Liu, Han and Zhang, Tong and Ba{\c{s}}ar, Tamer},
  journal = {IEEE Transactions on Automatic Control},
  volume = 66,
  number = 12,
  pages = {5925--5940},
  year = 2021,
  publisher = {IEEE},
  url = {https://arxiv.org/pdf/1812.02783},
  doi = {10.1109/TAC.2021.3049345}
}

@article{FDZ-21,
  author = {Cong Fang and Hanze Dong and Tong Zhang},
  title = {Mathematical Models of Overparameterized Neural Networks},
  journal = {Proceedings of the IEEE},
  url = {https://arxiv.org/pdf/2012.13982},
  volume = 109,
  number = 5,
  pages = {683--703},
  year = 2021
}

@article{YMWZ21,
  author = {Minghan Yang and Andre Milzarek and Zaiwen Wen and Tong Zhang},
  title = {A Stochastic Extra-Step Quasi-Newton Method for Nonsmooth Nonconvex Optimization},
  journal = {Mathematical Programming},
  url = {https://arxiv.org/pdf/1910.09373},
  doi = {https://doi.org/10.1007/s10107-021-01629-y},
  year = 2021
}

@article{YeZh21,
  author = {Haishan Ye and Tong Zhang},
  title = {De{EPCA}: Decentralized Exact {PCA} with  Linear Convergence Rate},
  journal = {Journal of Machine Learning Research},
  year = 2021,
  volume = 22,
  number = 238,
  pages = {1-27},
  url = {http://jmlr.org/papers/v22/21-0298.html}
}

@article{FGZZ22-tit,
  author = {Cong Fang and Yihong Gu and Weizhong Zhang and Tong Zhang},
  title = {Convex Formulation of Overparameterized Deep Neural Networks},
  journal = {IEEE Transactions on Information Theory},
  year = 2022,
  volume = 68,
  number = 8,
  pages = {5340-5352},
  url = {https://ieeexplore.ieee.org/document/9745067}
}

@article{Zhang22-ts,
  author = {Zhang, Tong},
  title = {Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning},
  journal = {SIAM Journal on Mathematics of Data Science},
  volume = 4,
  number = 2,
  pages = {834-857},
  year = 2022,
  doi = {10.1137/21M140924X},
  url = {      https://doi.org/10.1137/21M140924X}
}

@article{shen2022disentangled,
  title = {Weakly Supervised Disentangled generative causal representation learning},
  author = {Shen, Xinwei and Liu, Furui and Dong, Hanze and Lian, Qing and Chen, Zhitang and Zhang, Tong},
  journal = {JMLR},
  volume = 23,
  pages = {1--55},
  url = {https://www.jmlr.org/papers/v23/21-0080.html},
  year = 2022
}

@article{FrMaZh2022-SGLD,
  author = {Yoav Freund and Yi-An Ma and Tong Zhang},
  title = {When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint},
  journal = {Journal of Machine Learning Research},
  year = {2022},
  volume = {23},
  number = {214},
  pages = {1--32},
  url = {http://jmlr.org/papers/v23/21-1489.html}
}

@article{diao2022black,
  title = {Black-box prompt learning for pre-trained language models},
  author = {Diao, Shizhe and Li, Xuechun and Lin, Yong and Huang, Zhichao and Zhang, Tong},
  journal = {Transactions on Machine Learning Research},
  url = {https://arxiv.org/abs/2201.08531},
  year = {2023}
}

@article{ye2020multi,
  author = {Haishan Ye and Luo Luo and Ziang Zhou and Tong Zhang},
  title = {Multi-Consensus Decentralized Accelerated Gradient Descent},
  journal = {Journal of Machine Learning Research},
  year = {2023},
  volume = {24},
  number = {306},
  pages = {1--50},
  url = {http://jmlr.org/papers/v24/22-1210.html}
}

@article{dong2023raft,
  title = { {RAFT}: Reward rAnked FineTuning for Generative Foundation Model Alignment},
  author = {Hanze Dong and Wei Xiong and Deepanshu Goyal and Yihan Zhang and Winnie Chow and Rui Pan and Shizhe Diao and Jipeng Zhang and KaShun SHUM and Tong Zhang},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2023},
  url = {https://openreview.net/forum?id=m7p5O7zblY}
}

@article{wang2024on,
  title = {On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data},
  author = {Jianyu Wang and Rudrajit Das and Gauri Joshi and Satyen Kale and Zheng Xu and Tong Zhang},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2024},
  url = {https://openreview.net/forum?id=zF76Ga4EPs}
}

@article{fan2023environmentinvariantlinearsquares,
  title = {Environment Invariant Linear Least Squares},
  author = {Jianqing Fan and Cong Fang and Yihong Gu and Tong Zhang},
  year = {2023},
  url = {https://arxiv.org/abs/2303.03092},
  journal = {Annals of Statistics},
  note = {to appear}
}

@article{dong2024rlhf,
  title = { {RLHF} Workflow: From Reward Modeling to Online {RLHF}},
  author = {Hanze Dong and Wei Xiong and Bo Pang and Haoxiang Wang and Han Zhao and Yingbo Zhou and Nan Jiang and Doyen Sahoo and Caiming Xiong and Tong Zhang},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2024},
  url = {https://openreview.net/forum?id=a13aYUU9eU}
}

@article{gentile2022fastratespoolbasedbatch,
  title = {Fast Rates in Pool-Based Batch Active Learning},
  author = {Claudio Gentile and Zhilei Wang and Tong Zhang},
  year = {2024},
  journal = {JMLR},
  url = {https://arxiv.org/abs/2202.05448},
  note = {to appear}
}

@inproceedings{ZhOl00-icml,
  author = {Tong Zhang and Frank J. Oles},
  title = {A probability analysis on the value of unlabeled data for 
    classification problems},
  booktitle = {ICML 00},
  pages = {1191--1198},
  url = {http://tongzhang-ml.org/papers/icml00-unlabeled.pdf},
  year = 2000
}

@inproceedings{IAZ00,
  author = {Vijay S. Iyengar and  Chidanand Apte and Tong Zhang},
  title = {Active learning using adaptive resampling},
  booktitle = {The Sixth ACM SIGKDD International Conference on Knowledge 
                  Discovery and Data Mining},
  pages = {91--98},
  url = {http://tongzhang-ml.org/papers/kdd00-active.pdf},
  year = 2000
}

@inproceedings{Zhang00conv,
  author = {Tong Zhang},
  title = {Convergence of Large Margin Separable Linear Classification},
  booktitle = {Advances in Neural Information Processing Systems 13},
  pages = {357--363},
  url = {http://tongzhang-ml.org/papers/nips00-margin.pdf},
  year = 2000
}

@inproceedings{Zhang00winnow,
  author = {Tong Zhang},
  title = {Regularized {W}innow Methods},
  url = {http://tongzhang-ml.org/papers/nips00-rwinnow.pdf},
  booktitle = {Advances in Neural Information Processing Systems 13},
  pages = {703--709},
  year = 2000
}

@inproceedings{IZ01-pakdd,
  author = {Vijay S. Iyengar and Tong Zhang},
  title = {Empirical Study of Recommender Systems Using Linear Classifiers},
  booktitle = {The Fifth Pacific-Asia Conference on Knowledge 
                  Discovery and Data Mining},
  pages = {16--27},
  year = 2001
}

@inproceedings{Zhang01-sparse-icml,
  author = {Tong Zhang},
  title = {Some Sparse Approximation Bounds for Regression Problems},
  pages = {624--631},
  booktitle = {The Eighteenth International Conference on Machine Learning},
  fullref = {http://tongzhang-ml.org/papers/nc02_greedy.pdf},
  year = 2001
}

@inproceedings{ZDJ01-acl,
  author = {Tong Zhang and Fred Damerau and David E. Johnson},
  title = {Text Chunking using Regularized {W}innow},
  booktitle = {39th Annual Meeting of the Association for
                             Computational Linguistics},
  pages = {539--546},
  fullref = {http://tongzhang-ml.org/papers/jmlr02_chunking.pdf},
  year = 2001
}

@inproceedings{Zhang01-colt-seq,
  author = {Tong Zhang},
  title = {A Sequential Approximation Bound for Some Sample-Dependent
  Convex Optimization Problems with Applications in Learning},
  pages = {65--81},
  booktitle = {14th Annual Conference on Computational Learning Theory},
  url = {http://tongzhang-ml.org/papers/colt01-seq.pdf},
  year = 2001
}

@inproceedings{Zhang01-colt-loo,
  author = {Tong Zhang},
  title = {A Leave-one-out Cross Validation Bound for Kernel Methods
  with Applications in Learning},
  pages = {427--443},
  booktitle = {14th Annual Conference on Computational Learning Theory},
  fullref = {http://tongzhang-ml.org/papers/nc03_loo.pdf},
  year = 2001
}

@inproceedings{Zhang01-nips-greedy,
  author = {Tong Zhang},
  title = {A General Greedy Approximation Algorithm with Applications},
  booktitle = {Advances in Neural Information Processing Systems 14},
  editor = {T. G. Dietterich and S. Becker and Z. Ghahramani},
  publisher = {MIT Press},
  address = {Cambridge, MA},
  url = {http://tongzhang-ml.org/papers/nips01-greedy.pdf},
  fullref = {http://tongzhang-ml.org/papers/it03_greedy.pdf},
  year = 2001
}

@inproceedings{Zhang01-nips-gen,
  author = {Tong Zhang},
  title = {Generalization Performance of Some Learning Problems in {H}ilbert Functional Spaces},
  booktitle = {Advances in Neural Information Processing Systems 14},
  editor = {T. G. Dietterich and S. Becker and Z. Ghahramani},
  publisher = {MIT Press},
  address = {Cambridge, MA},
  url = {http://tongzhang-ml.org/papers/nips01-generr.pdf},
  year = 2001
}

@inproceedings{MMZ02,
  author = {Shie Mannor and Ron Meir and Tong Zhang},
  title = {The Consistency of Greedy Algorithms for Classification},
  booktitle = {COLT 02},
  year = 2002,
  url = {http://tongzhang-ml.org/papers/colt02-boost.pdf},
  fullref = {http://tongzhang-ml.org/papers/jmlr03-boost.pdf},
  pages = {319--333}
}

@inproceedings{Zhang02-consistency-icml,
  author = {Tong Zhang},
  title = {Statistical Behavior and Consistency of Support Vector Machines,
                  Boosting, and Beyond},
  booktitle = {ICML 02},
  pages = {690--697},
  fullref = {http://tongzhang-ml.org/papers/aos04_consistency.pdf},
  year = 2002
}

@inproceedings{Zhang02-nips-ker,
  author = {Tong Zhang},
  title = {Effective dimension and Generalization of Kernel Learning},
  booktitle = {NIPS 2002},
  fullref = {http://tongzhang-ml.org/papers/nc05-ker.pdf},
  year = 2002
}

@inproceedings{MeirZhang02-nips,
  author = {Ron Meir and Tong Zhang},
  title = {Data-Dependent Bounds for {B}ayesian Mixture Methods},
  booktitle = {NIPS 2002},
  fullref = {http://tongzhang-ml.org/papers/jmlr03-mixture.pdf},
  year = 2002
}

@inproceedings{DZWI02,
  author = {Fred J. Damerau and Tong Zhang and Sholom M. Weiss and Nitin Indurkhya},
  title = {Experiments in High-Dimensional Text Categorization},
  booktitle = {SIGIR 2002},
  fullref = {http://tongzhang-ml.org/papers/ipm04-new_reuters.pdf},
  year = 2002
}

@inproceedings{ZFJ03,
  author = {Tong Zhang and Fred Damerau and David E. Johnson},
  title = {Updating an NLP System to Fit New Domains: 
  an empirical study on the sentence segmentation problem},
  booktitle = {Proceedings CoNLL-2003},
  year = 2003,
  url = {http://tongzhang-ml.org/papers/conll03-adapt.pdf},
  pages = {56--62}
}

@inproceedings{FIJZ03,
  author = {Radu Florian and Abe Ittycheriah and Hongyan Jing and Tong Zhang},
  title = {Named Entity Recogintion through Classifier Combination},
  booktitle = {Proceedings CoNLL-2003},
  pages = {168--171},
  url = {http://tongzhang-ml.org/papers/conll03-fijz.pdf},
  year = 2003
}

@inproceedings{ZJ03,
  author = {Tong Zhang and David E. Johnson},
  title = {A Robust Risk Minimization based Named Entity Recognition System},
  booktitle = {Proceedings CoNLL-2003},
  pages = {204--207},
  url = {http://tongzhang-ml.org/papers/conll03-rrm.pdf},
  year = 2003
}

@inproceedings{ZhYu03,
  author = {Tong Zhang and Bin Yu},
  title = {On the Convergence of Boosting Procedures},
  booktitle = {ICML 03},
  year = 2003,
  fullref = {http://tongzhang-ml.org/papers/aos05-boost.pdf},
  pages = {904--911}
}

@inproceedings{JFLZI03,
  author = {Hongyan Jing and Radu Florian and Xiaoqiang Luo and Tong Zhang and Abraham Ittycheriah},
  title = {HowtogetaChineseName (Entity) : Segmentation and Combination Issues},
  booktitle = {EMNLP 2003},
  year = 2003,
  url = {http://tongzhang-ml.org/papers/emnlp03-chne.pdf},
  pages = {200-207}
}

@inproceedings{Zhang03-nips-bayes,
  author = {Tong Zhang},
  title = {Learning Bounds for a Generalized Family of {B}ayesian Posterior Distributions},
  booktitle = {NIPS 03},
  url = {http://tongzhang-ml.org/papers/nips03-bayes.pdf},
  year = 2003
}

@inproceedings{Zhang03-nips-mcat,
  author = {Tong Zhang},
  title = {An Infinity-sample Theory for Multi-category Large Margin Classification},
  booktitle = {NIPS 03},
  url = {http://tongzhang-ml.org/papers/nips03-multi_cat.pdf},
  year = 2003
}

@inproceedings{Zhang04-icml,
  author = {Tong Zhang},
  title = {Solving Large Scale Linear Prediction Problems Using
  Stochastic Gradient Descent Algorithms},
  booktitle = {ICML 04},
  year = 2004,
  url = {http://tongzhang-ml.org/papers/icml04-stograd.pdf},
  pages = {919--926}
}

@inproceedings{ZhPaZh04-sigir,
  author = {Li Zhang and Yue Pan and Tong Zhang},
  title = {Focused Named Entity Recognition using Machine Learning},
  booktitle = {SIGIR 04},
  url = {http://tongzhang-ml.org/papers/sigir04-focusedentity.pdf},
  year = 2004
}

@inproceedings{Zhang04-colt,
  author = {Tong Zhang},
  title = {On the Convergence of {MDL} Density Estimation},
  booktitle = {COLT 2004},
  year = 2004,
  url = {http://tongzhang-ml.org/papers/colt04-mdl.pdf},
  pages = {315--330}
}

@inproceedings{BiZhBe04,
  author = {Jinbo Bi and Tong Zhang and Kristin P. Bennett.},
  title = {Column-Generation Boosting Methods for Mixture of Kernels},
  booktitle = {KDD 2004},
  url = {http://tongzhang-ml.org/papers/kdd04-cgmix.pdf},
  year = 2004
}

@inproceedings{BiZh04-nips,
  author = {Jinbo Bi and Tong Zhang},
  title = {Support Vector Classification with Input Data Uncertainty},
  booktitle = {NIPS 04},
  url = {http://tongzhang-ml.org/papers/nips04-tsvc.pdf},
  year = 2004
}

@inproceedings{Zhang04-nips-multicat,
  author = {Tong Zhang},
  title = {Class-size Independent Generalization Analsysis of Some Discriminative Multi-Category Classification Methods},
  booktitle = {NIPS 04},
  url = {http://tongzhang-ml.org/papers/nips04-multicat_gen.pdf},
  year = 2004
}

@inproceedings{Zhang05-colt-minmax,
  author = {Tong Zhang},
  title = {Localized Upper and Lower Bounds for Some Estimation Problems},
  booktitle = {COLT 05},
  url = {http://tongzhang-ml.org/papers/colt05-minmax.pdf},
  year = 2005
}

@inproceedings{Zhang05-colt-online,
  author = {Tong Zhang},
  title = {Data Dependent Concentration Bounds for Sequential Prediction Algorithms},
  booktitle = {COLT 05},
  url = {http://tongzhang-ml.org/papers/colt05-seq.pdf},
  year = 2005
}

@inproceedings{TilZha05,
  author = {Christoph Tillmann and Tong Zhang},
  title = {A Localized Prediction Model for Statistical Machine Translation},
  booktitle = {ACL 05},
  url = {http://tongzhang-ml.org/papers/acl05-mt.pdf},
  year = 2005
}

@inproceedings{AndoZha05,
  author = {Rie Kubota Ando and Tong Zhang},
  title = {A High-Performance Semi-Supervised Learning Method for  Text Chunking},
  booktitle = {ACL 05},
  url = {http://tongzhang-ml.org/papers/acl05-semi.pdf},
  year = 2005
}

@inproceedings{AndoZha05nips,
  author = {Tong Zhang and Rie K. Ando},
  title = {Analysis of Spectral Kernel Design based Semi-supervised Learning},
  booktitle = {NIPS 05},
  fullref = {http://tongzhang-ml.org/papers/it08-graph.pdf},
  year = 2005
}

@inproceedings{CossZha06:colt,
  author = {David Cossock and Tong Zhang},
  title = {Subset Ranking using Regression},
  booktitle = {Proc. COLT'06},
  fullref = {http://tongzhang-ml.org/papers/it08-ranking.pdf},
  year = 2006
}

@inproceedings{TilZha06,
  author = {Christoph Tillmann and Tong Zhang},
  title = {A Discriminative Global Training Algorithm for Statistical {MT}},
  booktitle = {ACL'06},
  url = {http://tongzhang-ml.org/papers/acl06-mt.pdf},
  fullref = {http://tongzhang-ml.org/papers/taslp08-mt.pdf},
  year = 2006
}

@inproceedings{ZhaPopDom06,
  author = {Tong Zhang and Alexandrin Popescul and Byron Dom},
  title = {Linear Prediction Models with Graph Regularization for Web-page Categorization},
  booktitle = {KDD'06},
  url = {http://tongzhang-ml.org/papers/kdd06-graph.pdf},
  year = 2006
}

@inproceedings{AndoZhang06,
  author = {Rie K. Ando and Tong Zhang},
  title = {Learning on Graph with {L}aplacian Regularization},
  booktitle = {NIPS'06},
  fullref = {http://tongzhang-ml.org/papers/jmlr07-graph.pdf},
  year = 2006
}

@inproceedings{AndoZhang07,
  author = {Rie K. Ando and Tong Zhang},
  title = {Two-view Feature Generation Model for Semi-supervised Learning},
  booktitle = {ICML'07},
  url = {http://tongzhang-ml.org/papers/icml07-twoview.pdf},
  year = 2007
}

@inproceedings{BalBroZha07,
  author = {Maria-Florina Balcan and Andrei Broder and Tong Zhang},
  title = {Margin Based Active Learning},
  booktitle = {COLT'07},
  url = {http://tongzhang-ml.org/papers/colt07-active.pdf},
  year = 2007
}

@inproceedings{BrFoGaJoZh07,
  author = {Andrei Broder and Marcus Fontoura and Evgeniy Gabrilovich and
Amruta Joshi and Vanja Josifovski and Tong Zhang},
  title = {Robust Classification of Rare Queries Using Web Knowledge},
  booktitle = {SIGIR'07},
  url = {http://tongzhang-ml.org/papers/sigir07.pdf},
  year = 2007
}

@inproceedings{LangZhang07,
  author = {John Langford and Tong Zhang},
  title = {The {E}poch-{G}reedy Algorithm for Multi-armed Bandits with Side Information},
  booktitle = {NIPS'07},
  url = {http://tongzhang-ml.org/papers/nips07-bandits.pdf},
  year = 2007
}

@inproceedings{ZZZCCS07,
  author = {Zhaohui Zheng and Hongyuan Zha and Tong Zhang and Olivier Chapelle and Keke Chen and Gordon Sun},
  title = {A General Boosting Method and its Application to Learning Ranking Functions for Web Search},
  booktitle = {NIPS'07},
  url = {http://tongzhang-ml.org/papers/nips07-ranking.pdf},
  year = 2007
}

@inproceedings{LLSZ08-nips,
  author = {John Langford and Lihong Li and Tong Zhang},
  title = {Sparse Online Learning via Truncated Gradient},
  booktitle = {NIPS'08},
  url = {http://tongzhang-ml.org/papers/nips08-sparseonline.pdf},
  year = 2008
}

@inproceedings{Zhang08-foba-nips,
  author = {Tong Zhang},
  title = {Adaptive Forward-Backward Greedy Algorithm for Sparse Learning with Linear Models},
  booktitle = {NIPS'08},
  url = {http://tongzhang-ml.org/papers/nips08-foba.pdf},
  coderef = {http://tongzhang-ml.org/code/foba.zip},
  fullref = {http://tongzhang-ml.org/papers/it11-foba.pdf},
  year = 2008
}

@inproceedings{Zhang08-multistage-nips,
  author = {Tong Zhang},
  title = {Multi-stage Convex Relaxation for Learning with Sparse Regularization},
  booktitle = {NIPS'08},
  url = {http://tongzhang-ml.org/papers/nips08-multistage.pdf},
  fullref = {http://jmlr.org/papers/v11/zhang10a.htm},
  coeref = {http://tongzhang-ml.org/code/muscor.zip},
  year = 2008
}

@inproceedings{HuZhMe09-icml,
  author = {Junzhou Huang and Tong Zhang and Dimitris Metaxas},
  title = {Learning with Structured Sparsity},
  booktitle = {International Conference on Machine Learning 2009},
  year = 2009,
  url = {http://tongzhang-ml.org/papers/icml09-sparsity.pdf},
  fullref = {http://tongzhang-ml.org/papers/jmlr11-structsparsity.pdf}
}

@inproceedings{LaSaZh09-icml,
  author = {John Langford and Ruslan Salakhutdinov and Tong Zhang},
  title = {Learning Nonlinear Dynamic Models},
  booktitle = {ICML' 09},
  url = {http://tongzhang-ml.org/papers/icml09-dm.pdf},
  year = 2009
}

@inproceedings{HKZ09-colt,
  author = {Daniel Hsu and Sham M. Kakade and Tong Zhang},
  title = {A Spectral Algorithm for Learning Hidden Markov Models},
  booktitle = {COLT' 09},
  url = {http://tongzhang-ml.org/papers/arxiv0811.4413.pdf},
  fullref = {http://tongzhang-ml.org/papers/arxiv0811.4413.pdf},
  year = 2009
}

@inproceedings{HKLZ09-nips,
  author = {Daniel Hsu and Sham M. Kakade and John Langford and Tong Zhang},
  title = {Multi-label prediction via compressed sensing},
  booktitle = {NIPS' 09},
  url = {http://tongzhang-ml.org/papers/nips09-multilabel.pdf},
  year = 2009
}

@inproceedings{YZG09-nips,
  author = {Kai Yu and Tong Zhang and Yihong Gong},
  title = {Nonlinear Learning using Local Coordinate Coding},
  booktitle = {NIPS' 09},
  url = {http://tongzhang-ml.org/papers/nips09-lcc.pdf},
  fullref = {http://tongzhang-ml.org/papers/tr-lcc.pdf},
  year = 2009
}

@inproceedings{YuZhang10-icml,
  author = {Kai Yu and Tong Zhang},
  title = {Improved Local Coordinate Coding using Local Tangents},
  booktitle = {ICML' 10},
  url = {http://tongzhang-ml.org/papers/icml10-lcc.pdf},
  year = 2010
}

@inproceedings{ZYZH10,
  author = {Xi Zhou and Kai Yu and Tong Zhang and Thomas Huang},
  title = {Image Classification using Super-Vector Coding of Local Image Descriptors},
  booktitle = {ECCV'10},
  url = {http://tongzhang-ml.org/papers/eccv10_supervect.pdf},
  year = 2010
}

@inproceedings{BHLZ10-nips,
  author = {Alina Beygelzimer and Daniel Hsu and John Langford and Tong Zhang},
  title = {Agnostic Active Learning Without Constraints},
  booktitle = {NIPS' 10},
  url = {https://arxiv.org/abs/1006.2588},
  year = 2010
}

@inproceedings{LZZY10-nips,
  author = {Yuanqing Lin and Tong Zhang and Shenghuo Zhu and Kai Yu},
  title = {Deep Coding Network},
  booktitle = {NIPS' 10},
  url = {http://tongzhang-ml.org/papers/nips10-oracle.pdf},
  year = 2010
}

@inproceedings{DHKKLRZ11,
  author = {Miroslav Dudik and Daniel Hsu and Satyen Kale and Nikos Karampatziakis and John Langford and Lev Reyzin and Tong Zhang},
  title = {Efficient Optimal Learning for Contextual Bandits},
  booktitle = {UAI'01},
  url = {http://tongzhang-ml.org/papers/uai11-bandits.pdf},
  fullref = {http://arxiv.org/abs/1106.2369},
  year = 2011
}

@inproceedings{DaiZha11-nips,
  author = {Dong Dai and Tong Zhang},
  title = {Greedy Model Averaging},
  booktitle = {NIPS' 11},
  url = {http://arxiv.org/abs/1203.2507},
  year = 2011
}

@inproceedings{LNCZGH11-nips,
  author = {Zhen Li and Huazhong Ning and Liangliang Cao and Tong Zhang, Yihong Gong, Thomas Huang},
  title = {Learning to Search Efficiently in High Dimensions},
  booktitle = {NIPS' 11},
  url = {http://tongzhang-ml.org/papers/nips11-lts.pdf},
  year = 2011
}

@inproceedings{ACHKSZ11-nips,
  author = {Animashree Anandkumar and Kamalika Chaudhuri and Daniel Hsu and Sham M. Kakade and Le Song and Tong Zhang},
  title = {Spectral Methods for Learning Multivariate Latent Tree Structure},
  booktitle = {NIPS' 11},
  url = {http://arxiv.org/abs/1107.1283},
  year = 2011
}

@inproceedings{HsShZh12-colt,
  author = {Daniel Hsu and Sham M. Kakade and Tong Zhang},
  title = {Random Design Analysis of Ridge Regression},
  booktitle = {COLT'12},
  fullref = {http://arxiv.org/abs/1106.2363},
  year = 2012
}

@inproceedings{XiaoZhang12-icml,
  author = { Lin Xiao and Tong Zhang},
  title = {A Proximal-Gradient Homotopy Method for the {L}1-Regularized Least-Squares Problem},
  booktitle = {ICML'12},
  fullref = {http://arxiv.org/abs/1203.3002},
  year = 2012
}

@inproceedings{GZDH12-nips,
  author = {Quanquan Gu and Tong Zhang and Chris Ding and Jiawei Han},
  title = {Selective Labeling via Error Bound Minimization},
  booktitle = {NIPS'12},
  url = {http://tongzhang-ml.org/papers/nips12-selectivelabeling.pdf},
  year = 2012
}

@inproceedings{ShamirZhang13,
  author = {Ohad Shamir and Tong Zhang},
  title = {Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes},
  booktitle = {ICML'13},
  url = {http://tongzhang-ml.org/papers/icml13-lastpredictor.pdf},
  year = 2013
}

@inproceedings{BaKaZh13,
  author = {Krishnakumar Balasubramanian and Kai Yu and Tong Zhang},
  title = {High-dimensional Joint Sparsity Random Effects Model for Multi-task Learning},
  booktitle = {UAI'13},
  url = {http://tongzhang-ml.org/papers/uai13-scc.pdf},
  year = 2013
}

@inproceedings{SchZha13-minibatch,
  author = {Shai Shalev-Schwartz and Tong Zhang},
  title = {Accelerated Mini-Batch Stochastic Dual Coordinate Ascent},
  booktitle = {NIPS' 13},
  url = {http://arxiv.org/abs/1305.2581},
  year = 2013
}

@inproceedings{JohZha13,
  author = {Rie Johnson and Tong Zhang},
  title = {Accelerating Stochastic Gradient Descent using Predictive Variance Reduction},
  booktitle = {NIPS' 13},
  url = {http://tongzhang-ml.org/papers/nips13-svrg.pdf},
  year = 2013
}

@inproceedings{LZCS14-kdd,
  author = {Mu Li and Tong Zhang and Yuqiang Chen and Alexander Smola},
  title = {Efficient Mini-batch Training for Stochastic Optimization},
  booktitle = {KDD},
  url = {http://tongzhang-ml.org/papers/kdd14.pdf},
  year = 2014
}

@inproceedings{ShaZha14-icml,
  author = {Shai Shalev-Shwartz and Tong Zhang},
  title = {Accelerated Proximal Stochastic Dual Coordinate Ascent for Regularized Loss Minimization},
  booktitle = {ICML' 14},
  fullref = {http://arxiv.org/abs/1309.2375},
  year = 2014
}

@inproceedings{ShSrZh14-icml,
  author = {Ohad Shamir and Nathan Srebro and Tong Zhang},
  title = {Communication-Efficient Distributed Optimization using an Approximate Newton-type Method},
  booktitle = {ICML' 14},
  url = {http://arxiv.org/abs/1312.7853},
  year = 2014
}

@inproceedings{YuLiZh14-icml,
  author = {Xiaotong Yuan and Ping Li and Tong Zhang},
  title = {Gradient Hard Thresholding Pursuit for Sparsity-Constrained Optimization},
  booktitle = {ICML' 14},
  url = {http://arxiv.org/abs/1311.5750},
  year = 2014
}

@inproceedings{LiZhZh14-colt,
  author = {Ping Li and Cun-Hui Zhang and Tong Zhang},
  title = {Compressed Counting Meets Compressed Sensing},
  booktitle = {COLT' 14},
  url = {http://arxiv.org/abs/1310.1076},
  year = 2014
}

@inproceedings{JohnsonZhang15-naccl,
  author = {Rie Johnson and Tong Zhang},
  title = {Effective Use of Word Order for Text Categorization with Convolutional Neural Networks},
  booktitle = {NAACL' 15},
  url = {http://arxiv.org/abs/1412.1058},
  coderef = {https://github.com/riejohnson/ConText},
  year = 2015
}

@inproceedings{ZhaoZhang15-icml-imp,
  author = {Peilin Zhao and Tong Zhang},
  title = {Stochastic Optimization with Importance Sampling for Regularized Loss Minimization},
  booktitle = {ICML' 15},
  url = {http://tongzhang-ml.org/papers/icml15-sois.pdf},
  year = 2015
}

@inproceedings{ZhaYanZhaLi15-icml-admm,
  author = {Peilin Zhao and Jinwei Yang and Tong Zhang and Ping Li},
  title = {Adaptive Stochastic Alternating Direction Method of Multipliers},
  booktitle = {ICML' 15},
  url = {http://tongzhang-ml.org/papers/icml15-asadmm.pdf},
  year = 2015
}

@inproceedings{TZXZZ15-www,
  author = {Tian Tian and Jun Zhu and Fen Xia and Xin Zhuang and Tong Zhang},
  title = {Crowd Fraud Detection in Internet Advertising},
  booktitle = {WWW' 15},
  url = {http://tongzhang-ml.org/papers/www15-fraud.pdf},
  year = 2015
}

@inproceedings{VaLiZh15-nips,
  author = {Daniel Vainsencher and Han Liu and Tong Zhang},
  title = {Local Smoothness in Variance Reduced Optimization},
  booktitle = {NIPS},
  url = {http://tongzhang-ml.org/papers/nips15-localsmooth.pdf},
  year = 2015
}

@inproceedings{QuRiZh15-nips,
  author = {Zheng Qu and Peter Richtarik and Tong Zhang},
  title = {Quartz: Randomized Dual Coordinate Ascent with Arbitrary Sampling},
  booktitle = {NIPS},
  url = {http://arxiv.org/abs/1411.5873},
  year = 2015
}

@inproceedings{JohnsonZhang15-nips,
  author = {Rie Johnson and Tong Zhang},
  title = {Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding},
  booktitle = {NIPS},
  url = {http://arxiv.org/abs/1504.01255},
  coderef = {https://github.com/riejohnson/ConText},
  year = 2015
}

@inproceedings{YWLEZ16-icml,
  author = {Zhuoran Yang and Zhaoran Wang and Han Liu and Yonina C. Eldar and Tong Zhang},
  title = {Sparse Nonlinear Regression: Parameter Estimation under Nonconvexity},
  booktitle = {ICML},
  url = {http://tongzhang-ml.org/papers/icml16-nonlinear.pdf},
  year = 2016
}

@inproceedings{JonsonZhang16-icml,
  author = {Rie Johnson and Tong Zhang},
  title = {Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/1602.02373},
  coderef = {https://github.com/riejohnson/ConText},
  year = 2016
}

@inproceedings{HZWZ16-kdd,
  author = {Lei Han and Yu Zhang and Xiu-Feng Wan and Tong Zhang},
  title = {Generalized Hierarchical Sparse Model for Arbitrary-Order Interactive Antigenic Sites Identification in Flu Virus Data},
  booktitle = {KDD' 16},
  url = {http://tongzhang-ml.org/papers/kdd16-ghsm.pdf},
  year = 2016
}

@inproceedings{HaZhZh16-kdd,
  author = {Lei Han and Yu Zhang and Tong Zhang},
  title = {Fast Component Pursuit for Large-Scale Inverse Covariance Estimation},
  booktitle = {KDD' 16},
  url = {http://tongzhang-ml.org/papers/kdd16-cop.pdf},
  year = 2016
}

@inproceedings{YLZ16-nips,
  author = {Xiaotong Yuan and Ping Li and Tong Zhang},
  title = {Exact Recovery of Hard Thresholding Pursuit},
  booktitle = {NIPS},
  url = {https://papers.nips.cc/paper_files/paper/2016/file/e9b73bccd1762555582b513ff9d02492-Paper.pdf},
  year = 2016
}

@inproceedings{YLZLL16-nips,
  author = {Xiaotong Yuan and Ping Li and Tong Zhang and Qingshan Liu and Guangcan Liu},
  title = {Learning Additive Exponential Family Graphical Models via $\ell_{2,1}$-norm Regularized $M$-Estimation},
  booktitle = {NIPS},
  url = {https://proceedings.neurips.cc/paper_files/paper/2016/file/ee26fc66b1369c7625333bedafbfcaf6-Paper.pdf},
  year = 2016
}

@inproceedings{JohZha17-acl,
  author = {Rie Johnson and Tong Zhang},
  title = {Deep Pyramid Convolutional Neural Networks for Text Categorization},
  booktitle = {ACL},
  url = {https://aclanthology.org/P17-1052/},
  coderef = {https://github.com/riejohnson/ConText},
  year = 2017
}

@inproceedings{WKSZ17-icml,
  author = {Jialei Wang and Mladen Kolar and Nathan Srebro and Tong Zhang},
  title = {Efficient Distributed Learning with Sparsity},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/1605.07991},
  year = 2017
}

@inproceedings{ZZLHZZ17-icml,
  author = {Wenpeng Zhang and Peilin Zhao and Wei Liu and Steven Hoi and Wenwu Zhu and Tong Zhang},
  title = {Projection-Free Distributed Online Learning in Networks},
  booktitle = {ICML},
  url = {http://proceedings.mlr.press/v70/zhang17g/zhang17g.pdf},
  year = 2017
}

@inproceedings{LYGHZZ17-nips,
  author = {Xingguo  Li and Lin  Yang and Jason  Ge and Jarvis  Haupt and Tong  Zhang and Tuo  Zhao},
  title = {On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning},
  booktitle = {NIPS},
  url = {https://arxiv.org/pdf/1706.06066.pdf},
  year = 2017
}

@inproceedings{LiWaZh17-nips,
  author = {Chris Junchi Li and Mengdi Wang and Tong Zhang},
  title = {Diffusion Approximations for Online Principal Component Estimation and Global Convergence},
  booktitle = {NIPS},
  url = {https://arxiv.org/abs/1808.09645},
  year = 2017
}

@inproceedings{ZhHoMaLiZh18-icml,
  author = {Weizhong Zhang and Bin Hong and Lin Ma and Wei Liu and Tong Zhang},
  title = {Safe Element Screening for Submodular Function Minimization},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/1805.08527},
  year = 2018
}

@inproceedings{WuHuHuZh18-icml,
  author = {Jiaxiang Wu and Weidong Huang and Junzhou Huang and Tong Zhang},
  title = {Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization},
  booktitle = {ICML},
  url = {http://proceedings.mlr.press/v80/wu18d/wu18d.pdf},
  year = 2018
}

@inproceedings{JohnsonZhang18-icml,
  author = {Rie Johnson and Tong Zhang},
  title = {Composite Functional Gradient Learning of Generative Adversarial Models},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v80/johnson18a/johnson18a.pdf},
  fullref = {http://tongzhang-ml.org/papers/tpami20-cfggan.pdf},
  coderef = {https://github.com/riejohnson/cfg-gan-pt},
  year = 2018
}

@inproceedings{SuTaLiZh18-icml,
  author = {Qiang Sun and Kean Ming Tan and Han Liu and Tong Zhang},
  title = {Graphical Nonconvex Optimization via an Adaptive Convex Relaxation},
  booktitle = {ICML},
  url = {http://proceedings.mlr.press/v80/sun18c/sun18c.pdf},
  year = 2018
}

@inproceedings{HaHuZh18-icml,
  author = {Lei Han and Yiheng Huang and Tong Zhang},
  title = {Candidates vs. Noises Estimation for Large Multi-Class Classification Problem},
  booktitle = {ICML},
  url = {http://proceedings.mlr.press/v80/han18a/han18a.pdf},
  year = 2018
}

@inproceedings{ZYLZB18-icml,
  author = {Kaiqing Zhang and Zhuoran Yang and Han Liu and Tong Zhang and Tamer Basar},
  title = {Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v80/zhang18n.html},
  year = 2018
}

@inproceedings{FLLZ18-nips,
  title = { {SPIDER}: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator},
  author = {Fang, Cong and Li, Chris Junchi and Lin, Zhouchen and Zhang, Tong},
  booktitle = {NIPS},
  year = 2018,
  url = {http://papers.nips.cc/paper/7349-spider-near-optimal-non-convex-optimization-via-stochastic-path-integrated-differential-estimator}
}

@inproceedings{CZTZ18-nips,
  author = {Jianfei Chen and Jun Zhu and Yee Whye Teh and Tong Zhang},
  title = {Stochastic Expectation Maximization with Variance Reduction},
  booktitle = {NIPS},
  url = {https://papers.nips.cc/paper/8021-stochastic-expectation-maximization-with-variance-reduction},
  year = 2018
}

@inproceedings{TZMML18-nips,
  author = {Conghui Tan and Tong Zhang and Shiqian Ma and Ji Liu},
  title = {Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity},
  booktitle = {NIPS},
  url = {https://papers.nips.cc/paper/8057-stochastic-primal-dual-method-for-empirical-risk-minimization-with-o1-per-iteration-complexity},
  year = 2018
}

@inproceedings{WXHSLZ18-nips,
  author = {Qing Wang and Jiechao Xiong and Lei Han and Peng Sun and Han Liu and Tong Zhang},
  title = {Exponentially Weighted Imitation Learning for Batched Historical Data},
  booktitle = {NIPS},
  url = {https://papers.nips.cc/paper/7866-exponentially-weighted-imitation-learning-for-batched-historical-data},
  year = 2018
}

@inproceedings{TGZZL18-nips,
  author = {Hanlin Tang and Shaoduo Gan and Ce Zhang and Tong Zhang and Ji Liu},
  title = {Communication Compression for Decentralized Training},
  booktitle = {NIPS},
  url = {https://papers.nips.cc/paper/7992-communication-compression-for-decentralized-training},
  year = 2018
}

@inproceedings{WWLZ18-nips,
  author = {Jianqiao Wangni and Jialei Wang and Ji Liu and Tong Zhang},
  title = {Gradient Sparsification for Communication-Efficient Distributed Optimization},
  booktitle = {NIPS},
  url = {https://papers.nips.cc/paper/7405-gradient-sparsification-for-communication-efficient-distributed-optimization},
  year = 2018
}

@inproceedings{FZSGXZ19-iclr,
  author = {Meng Fang and Cheng Zhou and Bei Shi and Boqing Gong and Jia Xu and Tong Zhang},
  title = { {DHER}: Hindsight Experience Replay for Dynamic Goals},
  booktitle = {ICLR},
  url = {https://openreview.net/forum?id=Byf5-30qFX},
  year = 2019
}

@inproceedings{HSDXWSLZ19-icml,
  author = {Lei Han and Peng Sun and Yali Du and Jiechao Xiong and Qing Wang and Xinghai Sun and Han Liu and Tong Zhang},
  title = {Grid-Wise Control for Multi-Agent Reinforcement Learning in Video Game AI},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v97/han19a},
  year = 2019
}

@inproceedings{LLWZZG19-icml,
  author = {Yandong Li and Lijun Li and Liqiang Wang and Tong Zhang and Boqing Gong},
  title = { {NATTACK}: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks},
  booktitle = {ICML},
  url = {http://proceedings.mlr.press/v97/li19g},
  year = 2019
}

@inproceedings{TLYZL19-icml,
  author = {Hanlin Tang and Xiangru Lian and Chen Yu and Tong Zhang and Ji Liu},
  title = { {DOUBLESQUEEZE}: Parallel Stochastic Gradient Descent with Double-passError-Compensated Compression},
  booktitle = {ICML},
  url = {https://arxiv.org/pdf/1905.05957.pdf},
  year = 2019
}

@inproceedings{LSZZ19-acl,
  author = {Miaofeng Liu and Yan Song and Hongbin Zou and Tong Zhang},
  title = {Reinforced Training Data Selection for Domain Adaptation},
  booktitle = {ACL},
  url = {https://aclanthology.org/P19-1189/},
  year = 2019
}

@inproceedings{WLXZ19-nips,
  author = {Qing Wang and Yingru Li and Jiechao Xiong and Tong Zhang},
  title = {Divergence-Augmented Policy Optimization},
  booktitle = {Neurips},
  url = {https://dl.acm.org/doi/pdf/10.5555/3454287.3454835},
  year = 2019
}

@inproceedings{FLZ19-colt,
  author = {Cong Fang and Zhouchen Lin and Tong Zhang},
  title = {Sharp Analysis for Nonconvex SGD Escaping from Saddle Points},
  booktitle = {COLT},
  url = {https://arxiv.org/abs/1902.00247},
  year = 2019
}

@inproceedings{HuaZha20-iclr,
  author = {Zhichao Huang and Tong Zhang},
  title = { Black-Box Adversarial Attack with Transferable Model-based Embedding},
  booktitle = {ICLR},
  url = {https://arxiv.org/abs/1911.07140},
  year = 2020
}

@inproceedings{HYSZ20-cvpr,
  author = {Chaoyang He and Haishan Ye and Li Shen and Tong Zhang},
  title = { {M}i{L}e{NAS}: Efficient Neural Architecture Search via Mixed-Level Reformulation},
  booktitle = {CVPR},
  url = {https://arxiv.org/abs/2003.12238},
  year = 2020
}

@inproceedings{JohZha20-icml,
  author = {Rie Johnson and Tong Zhang},
  title = {Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2006.16840},
  codenote = {GULF method for neural network training with improved generalization},
  coderef = {https://github.com/riejohnson/gulf},
  year = 2020
}

@inproceedings{LYHZ20-sreda,
  author = {Luo Luo and Haishan Ye and Zhichao Huang and Tong Zhang},
  title = {Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems},
  booktitle = {Neurips},
  url = {https://arxiv.org/abs/2001.03724},
  year = 2020
}

@inproceedings{SPXLKZ20-bridging,
  author = {Han Shi and Renjie Pi and Hang Xu and Zhenguo Li and James Tin-Yau Kwok and Tong Zhang},
  title = {Bridging the Gap between Sample-based and One-shot Neural Architecture Search with {BONAS}},
  booktitle = {Neurips},
  url = {https://arxiv.org/abs/1911.09336},
  year = 2020
}

@inproceedings{chen2020mean,
  title = {A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks},
  author = {Chen, Zixiang and Cao, Yuan and Gu, Quanquan and Zhang, Tong},
  url = {https://arxiv.org/abs/2002.04026},
  booktitle = {Neurips},
  year = 2020
}

@inproceedings{YZLZ20-decentralized,
  author = {Haishan Ye and Ziang Zhou and Luo Luo and Tong Zhang},
  title = {Decentralized Accelerated Proximal Gradient Descent},
  booktitle = {Neurips},
  url = {https://dl.acm.org/doi/pdf/10.5555/3495724.3497261},
  year = 2020
}

@inproceedings{ZGFLZ20-landscape,
  author = {Weizhong Zhang and Yihong Gu and Cong Fang and Jason Lee and Tong Zhang},
  title = {How to Characterize The Landscape of Overparameterized Convolutional Neural Networks},
  booktitle = {Neurips},
  url = {https://proceedings.neurips.cc/paper/2020/hash/2794f6a20ee0685f4006210f40799acd-Abstract.html},
  year = 2020
}

@inproceedings{tian2020improving,
  title = {Improving Chinese Word Segmentation with Wordhood Memory Networks},
  author = {Tian, Yuanhe and Song, Yan and Xia, Fei and Zhang, Tong and Wang, Yonggang},
  booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},
  pages = {8274--8285},
  url = {https://www.aclweb.org/anthology/2020.acl-main.734/},
  year = {2020}
}

@inproceedings{DBSZW20-zen,
  author = {Diao, Shizhe and Bai, Jiaxin and Song, Yan and Zhang, Tong and Wang, Yonggang},
  title = { {ZEN}: pre-training chinese text encoder enhanced by n-gram representations},
  booktitle = {Findings of EMNLP},
  codenote = {ZEN: n-gram enhanced BERT-like pretraining method for Chinese Text (in Pytorch)},
  url = {https://arxiv.org/abs/1911.00720},
  coderef = {https://github.com/sinovation/ZEN},
  year = 2020
}

@inproceedings{huang2021few,
  title = {Few-Shot Human Motion Transfer by Personalized Geometry and Texture Modeling},
  author = {Huang, Zhichao and Han, Xintong and Xu, Jia and Zhang, Tong},
  booktitle = {CVPR},
  url = {https://arxiv.org/abs/2103.14338},
  year = 2021
}

@inproceedings{zhou2021effective,
  title = {Effective Sparsification of Neural Networks with Global Sparsity Constraint},
  author = {Zhou, Xiao and Zhang, Weizhong and Xu, Hang and Zhang, Tong},
  url = {https://arxiv.org/abs/2105.01571},
  booktitle = {CVPR},
  year = {2021}
}

@inproceedings{li2021involution,
  title = {Involution: Inverting the inherence of convolution for visual recognition},
  author = {Li, Duo and Hu, Jie and Wang, Changhu and Li, Xiangtai and She, Qi and Zhu, Lei and Zhang, Tong and Chen, Qifeng},
  url = {https://arxiv.org/abs/2103.06255},
  booktitle = {CVPR},
  year = {2021}
}

@inproceedings{DXSJSZ2021acl,
  author = {Shizhe Diao and Ruijia Xu and Hongjin Su and Yilei Jiang and Yan Song and Tong Zhang},
  title = {Taming Pre-trained Language Models with {N}-gram Representations for Low-Resource Domain Adaptation},
  booktitle = {ACL},
  url = {https://aclanthology.org/2021.acl-long.259.pdf},
  year = 2021
}

@inproceedings{DSSSZ2021acl,
  author = {Shizhe Diao and Xinwei Shen and Kashun Shum and Yan Song and Tong Zhang,},
  title = { {TILGAN}: Transformer-based Implicit Latent {GAN} for Diverse and Coherent Text Generation},
  booktitle = {Findings of ACL},
  url = {https://aclanthology.org/2021.findings-acl.428.pdf},
  year = 2021
}

@inproceedings{DYZZ2021-kdd,
  author = {Yuhui Ding and Quanming Yao and Huan Zhao and Tong Zhang},
  title = {DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks},
  booktitle = {KDD},
  url = {https://arxiv.org/abs/2010.03250},
  coderef = {https://github.com/AutoML-Research/DiffMG},
  year = 2021
}

@inproceedings{FLYZ2021-colt,
  author = {Cong Fang and Jason D. Lee and Pengkun Yang and Tong Zhang},
  title = {Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks},
  booktitle = {COLT},
  url = {https://arxiv.org/abs/2007.01452},
  year = 2021
}

@inproceedings{ZZCDZ2021-neurips,
  author = {Xiao Zhou and Weizhong Zhang and Zonghao Chen and Shizhe Diao and Tong Zhang},
  title = {Efficient Neural Network Training via Forward and Backward Propagation Sparsification},
  booktitle = {Neurips},
  url = {https://proceedings.neurips.cc/paper/2021/hash/80f2f15983422987ea30d77bb531be86-Abstract.html},
  year = 2021
}

@inproceedings{QRZ2021-neurips,
  author = {Xun Qian and Peter Richtarik and Tong Zhang},
  title = {Error Compensated Distributed SGD can be Accelerated},
  booktitle = {Neurips},
  url = {https://proceedings.neurips.cc/paper/2021/hash/ff1ced3097ccf17c1e67506cdad9ac95-Abstract.html},
  year = 2021
}

@inproceedings{DMZZ2021-neurips,
  author = {Christoph Dann and Mehryar Mohri and Tong Zhang and Julian Zimmert},
  title = {A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning},
  booktitle = {Neurips},
  url = {https://arxiv.org/abs/2208.10904},
  year = 2021
}

@inproceedings{PYZ22-iclr-eigencurve,
  title = {Eigencurve: Optimal Learning Rate Schedule for {SGD} on Quadratic Objectives with Skewed Hessian Spectrums},
  author = {Rui Pan and Haishan Ye and Tong Zhang},
  booktitle = {International Conference on Learning Representations},
  year = {2022},
  url = {https://openreview.net/forum?id=rTAclwH46Tb}
}

@inproceedings{LLZZL22-iclr-hyperdqn,
  title = {Hyper{DQN}: A Randomized Exploration Method for Deep Reinforcement Learning},
  author = {Ziniu Li and Yingru Li and Yushun Zhang and Tong Zhang and Zhi-Quan Luo},
  booktitle = {International Conference on Learning Representations},
  year = {2022},
  url = {https://openreview.net/forum?id=X0nrKAXu7g-}
}

@inproceedings{LDWZ22-cvpr-irm,
  title = {Bayesian Invariant Risk Minimization},
  author = {Yong Lin and Hanze Dong and Hao Wang and Tong Zhang},
  booktitle = {CVPR},
  url = {https://openaccess.thecvf.com/content/CVPR2022/papers/Lin_Bayesian_Invariant_Risk_Minimization_CVPR_2022_paper.pdf},
  year = {2022}
}

@inproceedings{LYXYZ22-cvpr-detection,
  title = {Exploring Geometric Consistency for Monocular 3D Object Detection},
  author = {Qing Lian and Botao Ye and Ruijia Xu and Weilong Yao and Tong Zhang},
  booktitle = {CVPR},
  url = {https://arxiv.org/abs/2104.05858},
  year = {2022}
}

@inproceedings{SZSZ22-acl,
  author = {Ying Su and Hongming Zhang and Yangqiu Song and Tong Zhang},
  title = {Rare and Zero-shot Word Sense Disambiguation using Z-Reweighting},
  booktitle = {ACL},
  url = {https://aclanthology.org/2022.acl-long.323/},
  year = 2022
}

@inproceedings{AgaZha22-colt-ts,
  author = {Alekh Agarwal and Tong Zhang},
  title = {Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling},
  booktitle = {COLT},
  url = {https://arxiv.org/abs/2203.08248},
  year = 2022
}

@inproceedings{AgaZha22-colt-mro,
  author = {Alekh Agarwal and Tong Zhang},
  title = {Minimax Regret Optimization for Robust Machine Learning under Distribution Shift},
  booktitle = {COLT},
  url = {https://arxiv.org/abs/2202.05436},
  year = 2022
}

@inproceedings{GWZ22-icml-active,
  author = {Claudio Gentile and Zhilei Wang and Tong Zhang},
  title = {Achieving Minimax Rates in Pool-Based Batch Active Learning},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2202.05448},
  year = 2022
}

@inproceedings{ZLPZXPZ-icml-maple,
  author = {Xiao Zhou and Yong Lin and Renjie Pi and Weizhong Zhang and Renzhe Xu and Cui Peng and Tong Zhang},
  title = {Model Agnostic Sample Reweighting for Out-of-Distribution Learning},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v162/zhou22d.html},
  year = 2022
}

@inproceedings{ZPZLZ-icml-coreset,
  author = {Xiao Zhou and Renjie PI and Weizhong Zhang and Yong Lin and Tong Zhang},
  title = {Probabilistic Bilevel Coreset Selection},
  url = {https://proceedings.mlr.press/v162/zhou22h.html},
  booktitle = {ICML},
  year = 2022
}

@inproceedings{XZSSZ-icml-ts-game,
  author = {Wei Xiong and Han Zhong and Chengshuai Shi and Cong Shen and Tong Zhang},
  title = {A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games},
  booktitle = {ICML},
  url = {https://proceedings.mlr.press/v162/xiong22b.html},
  year = 2022
}

@inproceedings{ZXTWZWY-icml-offline-game,
  author = {Han Zhong and Wei Xiong and Jiyuan Tan and Liwei Wang and Tong Zhang and Zhaoran Wang and Zhuoran Yang},
  title = {Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets},
  url = {https://proceedings.mlr.press/v162/zhong22b.html},
  booktitle = {ICML},
  year = 2022
}

@inproceedings{ZLZZ-icml-sparse-irm,
  author = {Xiao Zhou and Yong Lin and Weizhong Zhang and Tong Zhang},
  title = {Sparse Invariant Risk Minimization},
  url = {https://proceedings.mlr.press/v162/zhou22e.html},
  booktitle = {ICML},
  year = 2022
}

@inproceedings{agarwal2022model,
  author = {Agarwal, Alekh and Zhang, Tong},
  title = {Model-based {RL} with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity},
  booktitle = {Neurips},
  url = {https://arxiv.org/abs/2206.07659},
  year = 2022
}

@inproceedings{he2022nearly,
  author = {He, Jiafan and Zhou, Dongruo and Zhang, Tong and Gu, Quanquan},
  title = {Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptions},
  booktitle = {Neurips},
  url = {https://arxiv.org/abs/2205.06811},
  year = 2022
}

@inproceedings{dong2022particle,
  title = {Particle-based Variational Inference with Preconditioned Functional Gradient Flow},
  author = {Dong, Hanze and Wang, Xi and Lin, Yong and Zhang, Tong},
  booktitle = {ICLR},
  url = {https://arxiv.org/abs/2211.13954},
  year = {2023}
}

@inproceedings{xiong2022nearly,
  title = {Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game},
  author = {Xiong, Wei and Zhong, Han and Shi, Chengshuai and Shen, Cong and Wang, Liwei and Zhang, Tong},
  booktitle = {ICLR},
  url = {https://arxiv.org/abs/2205.15512},
  year = {2023}
}

@inproceedings{diao2023hashtag,
  author = {Shizhe Diao and Sedrick Scott Keh and Liangming Pan and Zhiliang Tian and Yan Song and Tong Zhang},
  title = {Hashtag-Guided Low-Resource Tweet Classification},
  booktitle = {The Web Conference},
  url = {https://dl.acm.org/doi/abs/10.1145/3543507.3583194},
  year = 2023
}

@inproceedings{ye2022corruption,
  title = {Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes},
  author = {Ye, Chenlu and Xiong, Wei and Gu, Quanquan and Zhang, Tong},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2212.05949},
  year = 2023
}

@inproceedings{lee2023learning,
  title = {Learning in POMDPs is Sample-Efficient with Hindsight Observability},
  author = {Lee, Jonathan N and Agarwal, Alekh and Dann, Christoph and Zhang, Tong},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2301.13857},
  year = 2023
}

@inproceedings{cho2023convergence,
  title = {On the Convergence of Federated Averaging with Cyclic Client Participation},
  author = {Cho, Yae Jee and Sharma, Pranay and Joshi, Gauri and Xu, Zheng and Kale, Satyen and Zhang, Tong},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2302.03109},
  year = {2023}
}

@inproceedings{das2022beyond,
  title = {Beyond uniform lipschitz condition in differentially private optimization},
  author = {Das, Rudrajit and Kale, Satyen and Xu, Zheng and Zhang, Tong and Sanghavi, Sujay},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2206.10713},
  year = {2023}
}

@inproceedings{wang2023generalized,
  title = {Generalized Polyak Step Size for First Order Optimization with Momentum},
  author = {Xiaoyu Wang and Mikael Johansson and Tong Zhang},
  booktitle = {ICML},
  url = {https://arxiv.org/abs/2305.12939},
  year = 2023
}

@inproceedings{yang2023what,
  title = {What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?},
  author = {Rui Yang and Yong Lin and Xiaoteng Ma and Hao Hu and Chongjie Zhang and Tong Zhang},
  booktitle = {ICML},
  year = {2023},
  url = {https://arxiv.org/abs/2305.18882}
}

@inproceedings{diao2023mixture,
  title = {Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models' Memories},
  author = {Shizhe Diao and Tianyang Xu and Ruijia Xu and Jiawei Wang and Tong Zhang},
  booktitle = {ACL},
  year = 2023,
  url = {https://arxiv.org/abs/2306.05406}
}

@inproceedings{agarwal2022vo,
  title = {VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation},
  author = {Agarwal, Alekh and Jin, Yujia and Zhang, Tong},
  booktitle = {COLT},
  url = {https://arxiv.org/abs/2212.06069},
  year = {2023}
}

@inproceedings{zhao2023variance,
  title = {Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency},
  author = {Zhao, Heyang and He, Jiafan and Zhou, Dongruo and Zhang, Tong and Gu, Quanquan},
  booktitle = {COLT},
  url = {https://arxiv.org/abs/2302.10371},
  year = {2023}
}

@inproceedings{pmlr-v206-qian23a,
  title = {Catalyst Acceleration of Error Compensated Methods Leads to Better Communication Complexity},
  author = {Qian, Xun and Dong, Hanze and Zhang, Tong and Richtarik, Peter},
  booktitle = {Proceedings of The 26th International Conference on Artificial Intelligence and Statistics},
  year = {2023},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v206/qian23a.html}
}

@inproceedings{blanchet2023double,
  title = {Double pessimism is provably efficient for distributionally robust offline reinforcement learning: Generic algorithm and robust partial coverage},
  author = {Blanchet, Jose and Lu, Miao and Zhang, Tong and Zhong, Han},
  booktitle = {Neurips},
  year = 2023,
  url = {https://arxiv.org/abs/2305.09659}
}

@inproceedings{zhong2023theoretical,
  title = {A theoretical analysis of optimistic proximal policy optimization in linear markov decision processes},
  author = {Zhong, Han and Zhang, Tong},
  booktitle = {Neurips},
  year = {2023},
  url = {https://arxiv.org/abs/2305.08841}
}

@inproceedings{johnson2023inconsistency,
  title = {Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training},
  author = {Johnson, Rie and Zhang, Tong},
  booktitle = {Neurips},
  year = {2023},
  url = {https://arxiv.org/abs/2306.00169}
}

@inproceedings{YYGZ2023corruption,
  author = {Chenlu Ye and Rui Yang and Quanquan Gu and Tong Zhang},
  title = {Corruption-Robust Offline Reinforcement Learning with General Function Approximation},
  booktitle = {Neurips},
  url = {https://arxiv.org/abs/2310.14550},
  year = 2023
}

@inproceedings{QDZWYZ2023posterior,
  author = {Shuang Qiu and Ziyu Dai and Han Zhong and Zhaoran Wang and Zhuoran Yang and Tong Zhang},
  title = {Posterior Sampling for Competitive RL: Function Approximation and Partial Observation},
  booktitle = {Neurips},
  url = {https://arxiv.org/abs/2310.19861},
  year = 2023
}

@inproceedings{LiFaZh23,
  author = {Yuanshi Liu and Cong Fang and Tong Zhan},
  title = {Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee},
  booktitle = {Neurips},
  url = {https://openreview.net/pdf?id=eTMHsUp3Ii},
  year = 2023
}

@inproceedings{pi2023detgpt,
  title = {Det{GPT}: Detect What You Need via Reasoning},
  author = {Pi, Renjie and Gao, Jiahui and Diao, Shizhe and Pan, Rui and Dong, Hanze and Zhang, Jipeng and Yao, Lewei and Han, Jianhua and Xu, Hang and Kong, Lingpeng and Zhang, Tong},
  booktitle = {The 2023 Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  url = {https://arxiv.org/abs/2305.14167}
}

@inproceedings{shum2023automatic,
  title = {Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data},
  author = {Shum, KaShun and Diao, Shizhe and Zhang, Tong},
  booktitle = {Findings of EMNLP 2023},
  year = {2023},
  url = {https://arxiv.org/abs/2302.12822}
}

@inproceedings{diao2023doolittle,
  title = {Doolittle: Benchmarks and Corpora for Academic Writing Formalization},
  author = {Shizhe Diao and Yongyu Lei and Liangming Pan and Tianqing Fang and Wangchunshu Zhou and Sedrick Scott Keh and Min-Yen Kan and Tong Zhang},
  booktitle = {The 2023 Conference on Empirical Methods in Natural Language Processing},
  year = {2023},
  url = {https://openreview.net/attachment?id=B3rTZovgaA&name=pdf}
}

@inproceedings{lin2024spurious,
  title = {Spurious Feature Diversification Improves Out-of-distribution Generalization},
  author = {Yong Lin and Lu Tan and Yifan Hao and Ho Nam Wong and Hanze Dong and Weizhong Zhang and Yujiu Yang and Tong Zhang},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=d6H4RBi7RH}
}

@inproceedings{pan2024accelerated,
  title = {Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise},
  author = {Rui Pan and Yuxing Liu and Xiaoyu Wang and Tong Zhang},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=CIqjp9yTDq}
}

@inproceedings{yang2024towards,
  title = {Towards Robust Offline Reinforcement Learning under Diverse Data Corruption},
  author = {Rui Yang and Han Zhong and Jiawei Xu and Amy Zhang and Chongjie Zhang and Lei Han and Tong Zhang},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=5hAMmCU0bK}
}

@inproceedings{huang2024reverse,
  title = {Reverse Diffusion Monte Carlo},
  author = {Xunpeng Huang and Hanze Dong and Yifan Hao and Yian Ma and Tong Zhang},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
  url = {https://openreview.net/forum?id=kIPEyMSdFV}
}

@inproceedings{paat2023medl,
  author = {Paat, Helbert and Lian, Qing and Yao, Weilong and Zhang, Tong},
  title = {MEDL-U: Uncertainty-aware 3D Automatic Annotator based on Evidential Deep Learning},
  booktitle = {ICRA},
  year = 2024,
  url = {https://arxiv.org/abs/2309.09599}
}

@inproceedings{pi2023perceptiongpt,
  title = {Perception{GPT}: Effectively Fusing Visual Perception into {LLM}},
  author = {Pi, Renjie and Yao, Lewei and Gao, Jiahui and Zhang, Jipeng and Zhang, Tong},
  booktitle = {Conference on Computer Vision and Pattern Recognition 2024},
  year = {2024},
  url = {https://arxiv.org/abs/2311.06612}
}

@inproceedings{zhang2023r,
  title = {R-tuning: Teaching large language models to refuse unknown questions},
  author = {Zhang, Hanning and Diao, Shizhe and Lin, Yong and Fung, Yi R and Lian, Qing and Wang, Xingyao and Chen, Yangyi and Ji, Heng and Zhang, Tong},
  booktitle = {NAACL' 24},
  year = 2024,
  url = {https://arxiv.org/abs/2311.09677}
}

@inproceedings{diao2023lmflow,
  author = {Shizhe Diao and Rui Pan and Hanze Dong and Ka Shun Shum and Jipeng Zhang and Wei Xiong and Tong Zhang},
  title = { {LMF}low: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models},
  booktitle = {NAACL' 24 (Demo Track)},
  year = 2024,
  url = {https://arxiv.org/abs/2306.12420}
}

@inproceedings{xiong2024gibbs,
  title = {Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint},
  author = {Wei Xiong and Hanze Dong and Chenlu Ye and Ziqi Wang and Han Zhong and Heng Ji and Nan Jiang and Tong Zhang},
  booktitle = {International Conference on Machine Learning},
  year = {2024},
  url = {https://arxiv.org/abs/2312.11456}
}

@inproceedings{agarwal2024the,
  title = {The Non-linear \$F\$-Design and Applications to Interactive Learning},
  author = {Alekh Agarwal and Jian Qian and Alexander Rakhlin and Tong Zhang},
  booktitle = {International Conference on Machine Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=MMMHufVc2v}
}

@inproceedings{zhang2024pessimism,
  title = {Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning},
  author = {Dake Zhang and Boxiang Lyu and Shuang Qiu and Mladen Kolar and Tong Zhang},
  booktitle = {International Conference on Machine Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=InUUQkExsw}
}

@inproceedings{huang2024faster,
  title = {Faster Sampling via Stochastic Gradient Proximal Sampler},
  author = {Xunpeng Huang and Difan Zou and Yian Ma and Hanze Dong and Tong Zhang},
  booktitle = {International Conference on Machine Learning},
  year = {2024},
  url = {https://openreview.net/forum?id=7gEcbhMqKU}
}

@inproceedings{ye2024towards,
  title = {Towards Robust Model-Based Reinforcement Learning Against Adversarial Corruption},
  author = {Chenlu Ye and Jiafan He and Quanquan Gu and Tong Zhang},
  booktitle = {International Conference on Machine Learning},
  year = {2024},
  url = {https://arxiv.org/abs/2402.08991}
}

@inproceedings{huang2024faster-diffusion,
  title = {Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo},
  author = {Huang, Xunpeng and Zou, Difan and Dong, Hanze and Ma, Yian and Zhang, Tong},
  booktitle = {COLT},
  year = 2024,
  url = {https://arxiv.org/abs/2401.06325}
}

@inproceedings{diao2023active,
  title = {Active Prompting with Chain-of-Thought for Large Language Models},
  author = {Diao, Shizhe and Wang, Pengcheng and Lin, Yong and Zhang, Tong},
  booktitle = {ACL},
  year = 2024,
  url = {https://arxiv.org/abs/2302.12246}
}

@inproceedings{pan2023plum,
  title = {Plum: Prompt learning using metaheuristic},
  author = {Pan, Rui and Xing, Shuo and Diao, Shizhe and Liu, Xiang and Shum, Kashun and Zhang, Jipeng and Zhang, Tong},
  booktitle = {Findings of ACL},
  year = 2023,
  url = {https://arxiv.org/abs/2311.08364}
}

@inproceedings{wang2024arithmetic,
  title = {Arithmetic Control of {LLM}s for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards},
  author = {Wang, Haoxiang and Lin, Yong and Xiong, Wei and Yang, Rui and Diao, Shizhe and Qiu, Shuang and Zhao, Han and Zhang, Tong},
  booktitle = {ACL},
  year = {2024},
  url = {https://arxiv.org/abs/2402.18571}
}

@inproceedings{wu2023ragtruth,
  title = {Ragtruth: A hallucination corpus for developing trustworthy retrieval-augmented language models},
  author = {Wu, Yuanhao and Zhu, Juno and Xu, Siliang and Shum, Kashun and Niu, Cheng and Zhong, Randy and Song, Juntong and Zhang, Tong},
  booktitle = {ACL},
  year = 2024,
  url = {https://arxiv.org/abs/2401.00396}
}

@inproceedings{wang2024enchancing,
  title = {Enhancing Dialogue State Tracking Models through {LLM}-backed User-Agents Simulation},
  author = {Xingguang Wang and Xuxin Cheng and Juntong Song and Tong Zhang and Cheng Niu},
  booktitle = {ACL},
  year = 2024,
  url = {https://openreview.net/forum?id=GbgnNdI1PH}
}

@inproceedings{pi2024strengthening,
  title = {Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization},
  author = {Pi, Renjie and Han, Tianyang and Xiong, Wei and Zhang, Jipeng and Liu, Runtao and Pan, Rui and Zhang, Tong},
  booktitle = {ECCV},
  year = 2024,
  url = {https://arxiv.org/abs/2403.08730}
}

@inproceedings{lin2023speciality,
  title = {Mitigating the Alignment Tax of {RLHF}},
  author = {Yong Lin and Hangyu Lin and Wei Xiong and Shizhe Diao and Jianmeng Liu and Jipeng Zhang and Rui Pan and Haoxiang Wang and Wenbin Hu and Hanning Zhang and Hanze Dong and Renjie Pi and Han Zhao and Nan Jiang and Heng Ji and Yuan Yao and Tong Zhang},
  booktitle = {The 2024 Conference on Empirical Methods in Natural Language Processing},
  year = {2024},
  url = {https://arxiv.org/abs/2309.06256}
}

@inproceedings{wang2024theoremllama,
  title = {TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts},
  author = {Wang, Ruida and Zhang, Jipeng and Jia, Yizhen and Pan, Rui and Diao, Shizhe and Pi, Renjie and Zhang, Tong},
  booktitle = {The 2024 Conference on Empirical Methods in Natural Language Processing},
  year = 2024,
  url = {https://arxiv.org/abs/2407.03203}
}

@inproceedings{pi2024mllm,
  title = { {MLLM}-Protector: Ensuring {MLLM}'s Safety without Hurting Performance},
  author = {Renjie Pi and Tianyang Han and Jianshu Zhang and Yueqi Xie and Rui Pan and Qing Lian and Hanze Dong and Jipeng Zhang and Tong Zhang},
  booktitle = {The 2024 Conference on Empirical Methods in Natural Language Processing},
  year = 2024,
  url = {https://arxiv.org/abs/2401.02906}
}

@inproceedings{han2024instinctive,
  title = {The Instinctive Bias: Spurious Images lead to Hallucination in MLLMs},
  author = {Han, Tianyang and Lian, Qing and Pan, Rui and Pi, Renjie and Zhang, Jipeng and Diao, Shizhe and Lin, Yong and Zhang, Tong},
  booktitle = {The 2024 Conference on Empirical Methods in Natural Language Processing},
  year = {2024},
  url = {https://arxiv.org/abs/2402.03757}
}

@inproceedings{wang2024interpretable,
  title = {Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts},
  author = {Wang, Haoxiang and Xiong, Wei and Xie, Tengyang and Zhao, Han and Zhang, Tong},
  booktitle = {Findings of EMNLP 2024},
  year = {2024},
  url = {https://arxiv.org/abs/2406.12845}
}

@inproceedings{pan2024lisa,
  title = { {LISA}: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning},
  author = {Pan, Rui and Liu, Xiang and Diao, Shizhe and Pi, Renjie and Zhang, Jipeng and Han, Chi and Zhang, Tong},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
  url = {https://arxiv.org/abs/2403.17919}
}

@inproceedings{wang2024clipsgeneralizebetterimagenet,
  title = {Do {CLIP} Models Always Generalize Better than ImageNet Models?},
  author = {Qizhou Wang and Yong Lin and Yongqiang Chen and Ludwig Schmidt and Bo Han and Tong Zhang},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
  url = {https://arxiv.org/abs/2403.11497}
}

@inproceedings{lu2024distributionallyrobustreinforcementlearning,
  title = {Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm},
  author = {Miao Lu and Han Zhong and Tong Zhang and Jose Blanchet},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
  url = {https://arxiv.org/abs/2404.03578}
}

@inproceedings{huang2024reversetransitionkernelflexible,
  title = {Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference},
  author = {Xunpeng Huang and Difan Zou and Hanze Dong and Yi Zhang and Yi-An Ma and Tong Zhang},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
  url = {https://arxiv.org/abs/2405.16387}
}

@inproceedings{ye2024onlineiterativereinforcementlearning,
  title = {Online Iterative Reinforcement Learning from Human Feedback with General Preference Model},
  author = {Chenlu Ye and Wei Xiong and Yuheng Zhang and Nan Jiang and Tong Zhang},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
  url = {https://arxiv.org/abs/2402.07314}
}

@inproceedings{yang2024regularizinghiddenstatesenables,
  title = {Regularizing Hidden States Enables Learning Generalizable Reward Model for {LLM}s},
  author = {Rui Yang and Ruomeng Ding and Yong Lin and Huan Zhang and Tong Zhang},
  booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems},
  year = {2024},
  url = {https://arxiv.org/abs/2406.10216}
}

@inproceedings{pi2024imagetextualizationautomaticframework,
  title = {Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions},
  author = {Renjie Pi and Jianshu Zhang and Jipeng Zhang and Rui Pan and Zhekai Chen and Tong Zhang},
  booktitle = {The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
  year = {2024},
  url = {https://arxiv.org/abs/2406.07502}
}

Tong Zhang

张潼

Publications