Yuxin Chen

I am an assistant professor of Electrical and Computer Engineering, and an associated faculty member of Computer Science, Applied and Computational Mathematics, and the Center for Statistics and Machine Learning at Princeton University. Prior to joining Princeton in Spring 2017, I was a postdoctoral scholar in the Department of Statistics at Stanford University supervised by Prof. Emmanuel Candès. I completed my Ph.D. in Electrical Engineering at Stanford University in Fall 2014, under the supervision of Prof. Andrea Goldsmith. Research areas: mathematical data science, statistics, reinforcement learning, optimization, information theory, and their applications to medical imaging and computational biology. Contact: C330, Engineering Quad Princeton University, Princeton, NJ 08544 Email: yuxin dot chen at princeton dot edu

Openings

I'm looking for highly motivated postdocs and Ph. D. students with strong mathematical background and interest in the general areas of statistics, optimization and reinforcement learning.

Recent news

• My second student Changxiao Cai has joined Prof. Tony Cai and Prof. Hongzhe Li's groups as a postdoc. Congratulations, Changxiao!!

• I received the 2021 Princeton SEAS junior faculty award.

• New monograph on spectral methods: “Spectral Methods for Data Science: A Statistical Perspective”.

• My first student Cong Ma has joined the Department of Statistics at the University of Chicago as an assistant professor. Congratulations, Cong!!

• Overview article: “Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview” [full version].

• I received the 2020 Princeton graduate mentoring award.

• I received the 2019 AFOSR Young Investigator Program (YIP) Award and the 2020 ARO YIP Award.

Teaching

• Fall 2020: ELE520: Mathematics of Data Science
  

• Fall 2020: ELE201: Information and Signals
  

• Fall 2019: ELE522: Large-Scale Optimization for Data Science (Princeton Engineering Commendation List for Outstanding Teaching)
  

Recent papers

• Reinforcement learning

  • G. Li, L. Shi, Y. Chen, Y. Gu, Y. Chi, “Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning,” NeurIPS 2021.

  • G. Li, Y. Chen, Y. Chi, Y. Gu, Y. Wei, “Sample-efficient reinforcement learning is feasible for linearly realizable MDPs with limited revisiting,” NeurIPS 2021.

  • W. Zhan*, S. Cen*, B. Huang, Y. Chen, J. D. Lee, Y. Chi, “Policy mirror descent for regularized reinforcement learning: A generalized framework with linear convergence,” 2021. (*=equal contributions)

  • G. Li, Y. Wei, Y. Chi, Y. Gu, Y. Chen, “Softmax policy gradient methods can take exponential time to converge,” 2021 (accepted in part to COLT 2021). [slides]

  • G. Li, C. Cai, Y. Chen, Y. Gu, Y. Wei, Y. Chi, “Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis,” 2021 (accepted in part to ICML 2021).

  • S. Cen, C. Cheng, Y. Chen, Y. Wei, Y. Chi, “Fast global convergence of natural policy gradient methods with entropy regularization,” accepted to Operations Research, 2021. [paper][slides]

  • G. Li, Y. Wei, Y. Chi, Y. Gu, Y. Chen, “Breaking the sample size barrier in model-based reinforcement learning with a generative model,” 2020 (accepted in part to NeurIPS 2020). [paper][slides]

  • G. Li, Y. Wei, Y. Chi, Y. Gu, Y. Chen, “Sample complexity of asynchronous Q-learning: Sharper analysis and variance reduction,” accepted to IEEE Transactions on Information Theory, 2021 (appeared in part to NeurIPS 2020). [paper][slides]

• Inference and uncertainty quantification

  • Y. Yan, Y. Chen, J. Fan, “Inference for heteroskedastic PCA with missing data,” 2021. [paper]

  • C. Cai, H. V. Poor, Y. Chen, “Uncertainty quantification for nonconvex tensor completion: Confidence intervals, heteroscedasticity and optimality,” 2020 (appeared in part in ICML 2020). [paper][slides]

  • Y. Chen, J. Fan, C. Ma, Y. Yan, “Inference and uncertainty quantification for noisy matrix completion,” Proceedings of the National Academy of Sciences (PNAS), vol. 116, no. 46, pp. 22931–22937, Nov. 2019. [Arxiv][PNAS version][slides]

• Nonconvex statistical learning and estimation

  • Y. Chen, J. Fan, C. Ma, Y. Yan, “Bridging convex and nonconvex optimization in robust PCA: Noise, outliers, and missing data,” accepted to Annals of Statistics, 2021. [paper]

  • Y. Chen, C. Ma, H. V. Poor, Y. Chen, “Learning Mixtures of Low-Rank Models,” IEEE Transactions on Information Theory, vol. 67, no. 7, pp. 4613-4636, July 2021. [paper]

  • Y. Chen, J. Fan, B. Wang, Y. Yan, “Convex and nonconvex optimization are both minimax-optimal for noisy blind deconvolution under random designs,” accepted to Journal of the American Statistical Association, 2021. [paper]

  • C. Cai, G. Li, H. V. Poor, Y. Chen, “Nonconvex low-rank tensor completion from noisy data,” accepted to Operations Research, 2020 (appeared in part in NeurIPS 2019). [paper][slides]

  • Y. Chen, Y. Chi, J. Fan, C. Ma, Y. Yan, “Noisy matrix completion: Understanding statistical guarantees for convex relaxation via nonconvex optimization,” SIAM Journal on Optimization, vol. 30, no. 4, pp. 3098–3121, October 2020. [paper][slides]

  • Y. Chen, Y. Chi, J. Fan, C. Ma, “Gradient descent with random initialization: Fast global convergence for nonconvex phase retrieval,” Mathematical Programming, vol. 176, no. 1-2, pp. 5-37, July 2019. [Arxiv][slides]

  • C. Ma, K. Wang, Y. Chi, Y. Chen, “Implicit regularization in nonconvex statistical estimation: Gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution,” Foundations of Computational Mathematics, vol. 20, no. 3, pp. 451-632, June 2020 (appeared in part in ICML 2018). [main text][supplement][full paper (Arxiv)][slides]

  • Y. Chen and E. J. Candes, “The projected power method: An efficient algorithm for joint alignment from pairwise differences,” Communications on Pure and Applied Mathematics, vol. 71, issue 8, pp. 1648-1714, August 2018. [slides][code]

  • Y. Chen and E. J. Candes, “Solving random quadratic systems of equations is nearly as easy as solving linear systems,” Communications on Pure and Applied Mathematics, vol. 70, issue 5, pp. 822-883, May 2017. [slides][website]

• Spectral methods

  • G. Li, C. Cai, Y. Gu, H. V. Poor, Y. Chen, “Minimax estimation of linear functions of eigenvectors in the face of small eigen-gaps,” 2021. [paper]

  • C. Cheng, Y. Wei, Y. Chen, “Tackling small eigen-gaps: Fine-grained eigenvector estimation and inference under heteroscedastic noise,” accepted to IEEE Transactions on Information Theory, 2020. [paper][slides]

  • C. Cai, G. Li, Y. Chi, H. V. Poor, Y. Chen, “Subspace estimation from unbalanced and incomplete data matrices, $\ell_{2,\infty}$ statistical guarantees ” Annals of Statistics, vol. 49, no. 2, pp. 944-967, 2021. [paper]

  • Y. Chen, C. Cheng, J. Fan, “Asymmetry helps: Eigenvalue and eigenvector analyses of asymmetrically perturbed low-rank matrices,” Annals of Statistics, vol. 49, no. 1, pp. 435-458, 2021. [paper][slides]

  • Y. Chen, J. Fan, C. Ma, K. Wang, “Spectral method and regularized MLE are both optimal for top-K ranking,” Annals of Statistics, vol. 47, no. 4, pp. 2204-2235, August 2019. [Arxiv][slides]