Publications

Selected papers

• Learning to Answer from Correct Demonstrations
  N. Joshi, G. Li, S. Bhandari, S. P. Kasiviswanathan, C. Ma, N. Srebro; ICLR, 2026 [Slides]

• Multi-Modal Contrastive Learning Adapts to Intrinsic Dimensions of Shared Latent Variables
  Y. Gui, C. Ma, Z. Ma; NeurIPS, 2025

• The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin
  R. Jiang, C. Ma; [Slides]

• The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
  X. Xu, Y. Shen, Y. Chi, C. Ma; ICML, 2023 [Slides]

• Optimally Tackling Covariate Shift in RKHS-Based Nonparametric Regression
  C. Ma, R. Pathak, M. J. Wainwright; Annals of Statistics, 2023 [Slides]

2025

• Learning to Answer from Correct Demonstrations
  N. Joshi, G. Li, S. Bhandari, S. P. Kasiviswanathan, C. Ma, N. Srebro; ICLR, 2026 [Slides]

• Multi-Modal Contrastive Learning Adapts to Intrinsic Dimensions of Shared Latent Variables
  Y. Gui, C. Ma, Z. Ma; NeurIPS, 2025

• The Adaptivity Barrier in Batched Nonparametric Bandits: Sharp Characterization of the Price of Unknown Margin
  R. Jiang, C. Ma; [Slides]

• IndiSeek Learns Information-Guided Disentangled Representations
  Y. Gui, C. Ma, Z. Ma

• Estimating Shared Subspace with AJIVE: The Power and Limitation of Multiple Data Matrices
  Y. Yang, C. Ma; [Slides]

2024

• Random Pairing MLE for Estimation of Item Parameters in Rasch Model
  Y. Yang, C. Ma; Journal of the American Statistical Association, 2025

• Trans-Glasso: A Transfer Learning Approach to Precision Matrix Estimation
  B. Zhao, C. Ma, M. Kolar; Journal of the American Statistical Association, 2025

• Batched Nonparametric Contextual Bandits
  R. Jiang, C. Ma; IEEE Transactions on Information Theory, 2025 [Slides]

• Top-K Ranking with a Monotone Adversary
  Y. Yang, A. Chen, L. Orecchia, C. Ma; COLT, 2024

• Off-Policy Estimation with Adaptively Collected Data: The Power of Online Learning
  J. Lee, C. Ma; NeurIPS, 2024

• Distributionally Robust Risk Evaluation with an Isotonic Constraint
  Y. Gui, R. F. Barber, C. Ma

• On the Design-Dependent Suboptimality of the Lasso
  R. Pathak, C. Ma; [Code]

2023

• Conformalized Matrix Completion
  Y. Gui, R. F. Barber, C. Ma; NeurIPS, 2023 [Code]

• The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing
  X. Xu, Y. Shen, Y. Chi, C. Ma; ICML, 2023 [Slides]

• High-Probability Sample Complexities for Policy Evaluation with Linear Function Approximation
  G. Li, W. Wu, Y. Chi, C. Ma, A. Rinaldo, Y. Wei; IEEE Transactions on Information Theory, 2024

• Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
  J. Ge, S. Tang, J. Fan, C. Ma, C. Jin; ICLR, 2024

• Unraveling Projection Heads in Contrastive Learning: Insights from Expansion and Shrinkage
  Y. Gui, C. Ma, Y. Zhong

2022

• Optimally Tackling Covariate Shift in RKHS-Based Nonparametric Regression
  C. Ma, R. Pathak, M. J. Wainwright; Annals of Statistics, 2023 [Slides]

• Optimal Tuning-Free Convex Relaxation for Noisy Matrix Completion
  Y. Yang, C. Ma; IEEE Transactions on Information Theory, 2023

• Fast and Provable Tensor Robust Principal Component Analysis via Scaled Gradient Descent
  H. Dong, T. Tong, C. Ma, Y. Chi; Information and Inference: A Journal of the IMA, 2023

• A New Similarity Measure for Covariate Shift with Applications to Nonparametric Regression
  R. Pathak, C. Ma, M. J. Wainwright (RP and CM contributed equally); ICML, 2022 (long presentation)

• Jump-Start Reinforcement Learning
  I. Uchendu, T. Xiao, Y. Lu, B. Zhu, M. Yan, J. Simon, M. Bennice, C. Fu, C. Ma, J. Jiao, S. Levine, K. Hausman; ICML, 2023

• \(O(1/T)\) Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
  Y. Yang, C. Ma; ICLR, 2023

• Pessimism for Offline Linear Contextual Bandits using \(\ell_{p}\) Confidence Sets
  G. Li, C. Ma, N. Srebro; NeurIPS, 2022 [Poster]

2021

• Minimax Off-Policy Evaluation for Multi-Armed Bandits
  C. Ma, B. Zhu, J. Jiao, M. J. Wainwright; IEEE Transactions on Information Theory, 2022 [Slides]

• Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
  P. Rashidinejad, B. Zhu, C. Ma, J. Jiao, S. Russell; IEEE Transactions on Information Theory, 2022, accepted in part to NeurIPS, 2021 [Slides]

• Scaling and Scalability: Provable Nonconvex Low-Rank Tensor Estimation from Incomplete Measurements
  T. Tong, C. Ma, A. Prater-Bennette, E. Tripp, Y. Chi; Journal of Machine Learning Research, 2022, accepted in part to AISTATS, 2022

• Modern Data Modeling: Cross-Fertilization of the Two Cultures
  J. Fan, C. Ma, K. Wang, Z. Zhu (alphabetical order); Observational Studies, 2021

2020

• Spectral Methods for Data Science: A Statistical Perspective
  Y. Chen, Y. Chi, J. Fan, C. Ma (alphabetical order); Foundations and Trends® in Machine Learning, 2021

• Bridging Convex and Nonconvex Optimization in Robust PCA: Noise, Outliers, and Missing Data
  Y. Chen, J. Fan, C. Ma, Y. Yan (alphabetical order); Annals of Statistics, 2021

• Learning Mixtures of Low-Rank Models
  Y. Chen, C. Ma, H. V. Poor, Y. Chen; IEEE Transactions on Information Theory, 2021

• Low-Rank Matrix Recovery with Scaled Subgradient Methods: Fast and Robust Convergence Without the Condition Number
  T. Tong, C. Ma, Y. Chi; IEEE Transactions on Signal Processing, 2021

• Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent
  T. Tong, C. Ma, Y. Chi; Journal of Machine Learning Research, 2021

• Comment on “A Tuning-Free Robust and Efficient Approach to High-Dimensional Regression”
  J. Fan, C. Ma, K. Wang (alphabetical order); Journal of the American Statistical Association, 2020

2019

• Inference and Uncertainty Quantification for Noisy Matrix Completion
  Y. Chen, J. Fan, C. Ma, Y. Yan (alphabetical order); Proceedings of the National Academy of Sciences, 2019 [Slides]

• A Selective Overview of Deep Learning
  J. Fan, C. Ma, Y. Zhong (alphabetical order); Statistical Science, 2020

• Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
  Y. Chen, Y. Chi, J. Fan, C. Ma, Y. Yan (alphabetical order); SIAM Journal on Optimization, 2020 [Slides]

• Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing
  C. Ma, Y. Li, Y. Chi; IEEE Transactions on Signal Processing, 2021, accepted in part to Asilomar 2019

2018

• Gradient Descent with Random Initialization: Fast Global Convergence for Nonconvex Phase Retrieval
  Y. Chen, Y. Chi, J. Fan, C. Ma (alphabetical order); Mathematical Programming, 2019 [Slides]

• Nonconvex Matrix Factorization from Rank-One Measurements
  Y. Li, C. Ma, Y. Chen, Y. Chi; IEEE Transactions on Information Theory, 2021, accepted in part to AISTATS, 2019

2017

• Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
  C. Ma, K. Wang, Y. Chi, Y. Chen; Foundations of Computational Mathematics, 2020, accepted in part to ICML, 2018 [Slides]

• Spectral Method and Regularized MLE Are Both Optimal for Top-K Ranking
  Y. Chen, J. Fan, C. Ma, K. Wang (alphabetical order); Annals of Statistics, 2019 [Slides]

• Inter-Subject Analysis: A Partial Gaussian Graphical Model Approach
  C. Ma, J. Lu, H. Liu; Journal of American Statistical Association, 2021 [Slides]

2015

• Fast and Flexible Top-K Similarity Search on Large Networks
  J. Zhang, J. Tang, C. Ma, H. Tong, Y. Jing, J. Li, W. Luyten, M. Moens; ACM Transactions on Information Systems, 2017, accepted in part to KDD, 2015