## Publications## Monographs and overview articles
## 2022**Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model** G. Li, Y. Chi, Y. Wei,__Y. Chen__, accepted to*Neural Information Processing Systems (NeurIPS)*, December 2022. [paper]**Model-Based Reinforcement Learning Is Minimax-Optimal for Offline Zero-Sum Markov Games** Y. Yan, G. Li,__Y. Chen__, J. Fan, 2022. [paper]**Settling the Sample Complexity of Model-Based Offline Reinforcement Learning** G. Li, L. Shi,__Y. Chen__, Y. Chi, Y. Wei, 2022. [paper]**The Efficacy of Pessimism in Asynchronous Q-Learning** Y. Yan, G. Li,__Y. Chen__, J. Fan, 2022. [paper]**Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity** L. Shi, G. Li, Y. Wei,__Y. Chen__, Y. Chi,*International Conference on Machine Learning (ICML)*, July 2022. [paper][ICML version]**MagNet: An Open-Source Database for Data-Driven Magnetic Core Loss Modeling** H. Li, D. Serrano, T. Guillod, E. Dogariu, A. Nadler, S. Wang, M. Luo, V. Bansal,__Y. Chen__, C. R. Sullivan, and M. Chen,*IEEE Applied Power Electronics Conference (APEC)*, 2022. [paper][Github repo][website]
## 2021**Breaking the Sample Complexity Barrier to Regret-Optimal Model-free Reinforcement Learning** G. Li, L. Shi,__Y. Chen__, Y. Chi, 2021. [paper][slides] — appeared in part in NeurIPS 2021**Inference for Heteroskedastic PCA with Missing Data** Y. Yan,__Y. Chen__, J. Fan, 2021. [paper]**Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting** G. Li,__Y. Chen__, Y. Chi, Y. Gu, Y. Wei,*Neural Information Processing Systems (NeurIPS)*, December 2021. [paper][NeurIPS version][slides]**Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence** W. Zhan*, S. Cen*, B. Huang,__Y. Chen__, J. D. Lee, Y. Chi, 2021. (*=equal contributions) [paper]**Minimax Estimation of Linear Functions of Eigenvectors in the Face of Small Eigen-Gaps** G. Li, C. Cai, H. V. Poor,__Y. Chen__, 2021. [paper]**Softmax Policy Gradient Methods Can Take Exponential Time to Converge** G. Li, Y. Wei, Y. Chi,__Y. Chen__, 2021. [paper][slides] — appeared in part in COLT 2021**Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis** G. Li, C. Cai,__Y. Chen__, Y. Wei, Y. Chi, 2021. [paper] — appeared in part in ICML 2021
## 2020**Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization** S. Cen, C. Cheng,__Y. Chen__, Y. Wei, Y. Chi,*Operations Research*, vol. 70, no. 4, pp. 2563–2578, 2022**(INFORMS George Nicholson award finalist, 2021)**. [paper][OR version][slides]**Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model** G. Li, Y. Wei, Y. Chi,__Y. Chen__, 2020. [paper][slides] — appeared in part in NeurIPS 2020**Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction** G. Li, Y. Wei, Y. Chi, Y. Gu,__Y. Chen__,*IEEE Transactions on Information Theory*, vol. 68, no. 1, pp. 448-473, Jan. 2022. [paper][slides] — appeared in part in NeurIPS 2020**Convex and Nonconvex Optimization Are Both Minimax-Optimal for Noisy Blind Deconvolution under Random Designs**
__Y. Chen__, J. Fan, B. Wang, Y. Yan, accepted to*Journal of the American Statistical Association*, 2020. [paper]**Uncertainty Quantification for Nonconvex Tensor Completion: Confidence Intervals, Heteroscedasticity and Optimality** C. Cai, H. V. Poor,__Y. Chen__, accepted to*IEEE Transactions on Information Theory*, 2022. [paper][slides] — appeared in part in ICML 2020**Bridging Convex and Nonconvex Optimization in Robust PCA: Noise, Outliers, and Missing Data**
__Y. Chen__, J. Fan, C. Ma, Y. Yan,*Annals of Statistics*, vol. 49, no. 5, pp. 2948-2971, Oct. 2021. [paper][AoS version]**Tackling Small Eigen-gaps: Fine-Grained Eigenvector Estimation and Inference under Heteroscedastic Noise** C. Cheng, Y. Wei,__Y. Chen__,*IEEE Transactions on Information Theory*, vol. 67, no. 11, pp. 7380-7419, Nov. 2021. [paper][slides]**Learning Mixtures of Low-Rank Models** Y. Chen, C. Ma, H. V. Poor,__Y. Chen__,*IEEE Transactions on Information Theory*, vol. 67, no. 7, pp. 4613-4636, July 2021. [paper]**MagNet: A Machine Learning Framework for Magnetic Core Loss Modeling** H. Li, S. R. Lee, M. Luo, C. R. Sullivan,__Y. Chen__, M. Chen,*IEEE Workshop on Control and Modeling of Power Electronics (COMPEL)*, 2020. [paper]
## 2019**Nonconvex Low-Rank Tensor Completion from Noisy Data** C. Cai, G. Li, H. V. Poor,__Y. Chen__,*Operations Research*, vol. 70, no. 2, pp. 1219–1237, 2022. [paper][OR version][slides] — appeared in part in NeurIPS 2019**Subspace Estimation from Unbalanced and Incomplete Data Matrices: $\ell_{2,\infty}$ Statistical Guarantees** C. Cai, G. Li, Y. Chi, H. V. Poor,__Y. Chen__,*Annals of Statistics*, vol. 49, no. 2, pp. 944-967, 2021. [paper][AoS version]**Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction** B. Li, S. Cen,__Y. Chen__, Y. Chi,*Journal of Machine Learning Research*, vol. 21, no. 180, pp. 1-51, 2020. [paper][code] — appeared in part in AISTATS 2020**Inference and Uncertainty Quantification for Noisy Matrix Completion**
__Y. Chen__, J. Fan, C. Ma, Y. Yan,*Proceedings of the National Academy of Sciences (PNAS)*, vol. 116, no. 46, pp. 22931–22937, Nov. 2019 (direct submission). [PNAS version][full paper][slides]**Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization**
__Y. Chen__, Y. Chi, J. Fan, C. Ma, Y. Yan,*SIAM Journal on Optimization*, vol. 30, no. 4, pp. 3098–3121, 2020. [paper][SIOPT version][slides]
## 2018**Gradient Descent with Random Initialization: Fast Global Convergence for Nonconvex Phase Retrieval**
__Y. Chen__, Y. Chi, J. Fan, C. Ma,*Mathematical Programming*, vol. 176, no. 1-2, pp. 5-37, July 2019. [paper][MP version][slides]**Nonconvex Matrix Factorization from Rank-One Measurements** Y. Li, C. Ma,__Y. Chen__, Y. Chi,*IEEE Transactions on Information Theory*, vol. 67, no. 3, pp. 1928-1950, March 2021. [paper] — appeared in part in AISTATS 2019**Asymmetry Helps: Eigenvalue and Eigenvector Analyses of Asymmetrically Perturbed Low-Rank Matrices**
__Y. Chen__, C. Cheng, J. Fan,*Annals of Statistics*, vol. 49, no. 1, pp. 435-458, 2021. [paper][AoS version][slides]
## 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*, vol. 20, no. 3, pp. 451-632, June 2020. [FoCM version][main text][supplement][Arxiv][slides] — appeared in part in ICML 2018**Spectral Method and Regularized MLE Are Both Optimal for Top-***K*Ranking
__Y. Chen__, J. Fan, C. Ma, K. Wang,*Annals of Statistics*, vol. 47, no. 4, pp. 2204-2235, August 2019. [paper][Arxiv][AoS version][slides]**The Likelihood Ratio Test in High-Dimensional Logistic Regression Is Asymptotically a***Rescaled*Chi-Square P. Sur,__Y. Chen__, E. J. Candes,*Probability Theory and Related Fields*, vol. 175, no. 1-2, pp.487–558, October 2019. [paper][supplement][slides][code]
## 2016**The Projected Power Method: An Efficient Algorithm for Joint Alignment from Pairwise Differences**
__Y. Chen__and E. J. Candes,*Communications on Pure and Applied Mathematics*, vol. 71, issue 8, pp. 1648-1714, August 2018. [paper][slides][code]**Community Recovery in Graphs with Locality**
__Y. Chen__, G. Kamath, C. Suh, and D. Tse,*International Conference on Machine Learning (ICML)*, June 2016. [paper][ICML version][CGSI slides][slides][Github repo][lecture by D. Tse]**Resolving Phase Ambiguity in Dual-Echo Dixon Imaging Using a Projected Power Method** T. Zhang,__Y. Chen__, S. Bao, M. Alley, J. M. Pauly, B. Hargreaves, S. S. Vasanawala,*Magnetic Resonance in Medicine*, vol. 77, no. 5, pp. 2066 - 2076, May 2017. [paper][webpage][code]
## 2015**Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems**
__Y. Chen__and E. J. Candes,*Communications on Pure and Applied Mathematics*, vol. 70, issue 5, pp. 822 - 883, May 2017. [paper][NIPS version][supplement][webpage and code][slides] — appeared in part in NIPS 2015**(oral)****Spectral MLE: Top-***K*Rank Aggregation from Pairwise Comparisons
__Y. Chen__and C. Suh,*International Conference on Machine Learning (ICML)*, July 2015. [paper][ICML version]**Information Recovery from Pairwise Measurements**
__Y. Chen__, C. Suh, and A. J. Goldsmith,*IEEE Trans. on Info. Theory*, vol. 62, no. 10, pp. 5881 - 5905, Oct. 2016. [paper][slides] — appeared in part in ISIT 2014 and ISIT 2015**Robust Self-Navigated Body MRI Using Dense Coil Arrays** T. Zhang, J. Y. Cheng,__Y. Chen__, D. G. Nishimura, J. M. Pauly, and S. S. Vasanawala,*Magnetic Resonance in Medicine*, vol. 76, no. 1, pp. 197 - 205, 2016. [paper][webpage][code]
## 2014**Near-Optimal Joint Object Matching via Convex Relaxation**
__Y. Chen__, L. Guibas, and Q. Huang,*International Conference on Machine Learning (ICML)*, June 2014. [paper][ICML version][slides][code]**Scalable Semidefinite Relaxation for Maximum A Posterior Estimation** Q. Huang,__Y. Chen__, and L. Guibas,*International Conference on Machine Learning (ICML)*, June 2014. [paper][slides]**Backing off from Infinity: Performance Bounds via Concentration of Spectral Measure for Random MIMO Channels**
__Y. Chen__, A. J. Goldsmith, and Y. C. Eldar,*IEEE Trans. on Info. Theory*, vol. 61, no. 1, pp. 366 - 387, Jan. 2015. [paper]
## 2013**Exact and Stable Covariance Estimation from Quadratic Sampling via Convex Programming**
__Y. Chen__, Y. Chi, and A. J. Goldsmith,*IEEE Trans. on Info. Theory*, vol. 61, no. 7, pp. 4034 - 4059, July 2015. [paper][slides] — appeared in part in ISIT 2014 and ICASSP 2014**Robust Spectral Compressed Sensing via Structured Matrix Completion**
__Y. Chen__and Y. Chi,*IEEE Trans. on Info. Theory*, vol. 60, no. 10, pp. 6576 - 6601, Oct. 2014. [paper][ICML version][slides] — appeared in part in ICML 2013 (full oral)**Compressive Two-Dimensional Harmonic Retrieval via Atomic Norm Minimization** Y. Chi and__Y. Chen__,*IEEE Trans. on Signal Processing*, vol. 63, no. 4, pp. 1030 - 1042, Feb. 2015. [paper]**Minimax Capacity Loss under Sub-Nyquist Universal Sampling**
__Y. Chen__, A. J. Goldsmith, and Y. C. Eldar,*IEEE Trans. on Info. Theory*, vol. 63, no. 6, pp. 3348 - 3367, June 2017. [paper][slides] — appeared in part in ISIT 2013
## 2012**Channel Capacity under Sub-Nyquist Nonuniform Sampling**
__Y. Chen__, A. J. Goldsmith, and Y. C. Eldar,*IEEE Trans. on Info. Theory*, vol. 60, no. 8, pp. 4739 - 4756, Aug. 2014. [paper] — appeared in part in ISIT 2012
## 2011**Shannon Meets Nyquist: Capacity of Sampled Gaussian Channels**
__Y. Chen__, Y. C. Eldar, and A. J. Goldsmith,*IEEE Trans. on Info. Theory*, vol. 59, no. 8, pp. 4889 - 4914 , Aug. 2013. [paper][slides] — appeared in part in ICASSP 2011**On the Role of Mobility on Multi-message Gossip**
__Y. Chen__, S. Shakkottai and J. G. Andrews,*IEEE Trans. on Info. Theory*, vol. 59, no. 6, pp. 3953 - 3970, June 2013. [paper][slides] — appeared in part in INFOCOM 2011 (full oral)
## 2010 |