Yuxin Chen

I am an associate professor of Statistics and Data Science
and of Electrical and Systems Engineering at
University of Pennsylvania.
Before moving to UPenn in 2022,
I was an assistant professor of Electrical and Computer Engineering, and an associated faculty member of Computer Science and Applied and Computational Mathematics at Princeton University from 2017 to 2021.
Prior to this, I was a postdoc in Statistics at Stanford University from 2015 to 2017, and obtained my Ph.D. in Electrical Engineering at Stanford University in Jan 2015.
Research areas: nonconvex optimization, statistics, reinforcement learning, information theory, and their applications to medical imaging, power electronics, and computational biology.
Contact:
313 Academic Research Building
265 South 37th Street, Philadelphia, PA 19104
Email: yuxinc at wharton dot upenn dot edu

Openings
I'm looking for highly motivated postdocs and Ph. D. students with strong mathematical background and interest in machine learning theory (particularly reinforcement learning, diffusion models, and LLM), statistics, and optimization.
Recent news

 Yuling Yan received the 2024 IMS Lawrence D. Brown Ph. D. Student Award. Congrats, Yuling!
 Changxiao Cai has joined University of MichiganAnn Arbor as an Assistant Professor of Industrial and Operations Engineering. Congrats, Changxiao!
 Gen Li has joined Chinese University of Hong Kong as an Assistant Professor of Statistics. Congrats, Gen!
 Yuling Yan will join University of WisconsinMadison as an Assistant Professor of Statistics in Fall 2024, after being a Norbert Wiener postdoc at MIT (advised by P. Rigollet and M. Wainwright). Congrats, Yuling!
 Qian Yu has joined UCSB as an Assistant Professor of Electrical and Computer Engineering. Congrats, Qian!

Topic courses I have developed
Selected recent papers
Machine learning theory
Z. Zhang, Y. Chen, J. D. Lee, S. S. Du, “Settling the sample complexity of online reinforcement learning,” 2023.
G. Li, Y. Wei, Y. Chen, Y. Chi, “Towards faster nonasymptotic convergence for diffusionbased generative models,” 2023.
G. Li, Y. Yan, Y. Chen, J. Fan, “Minimaxoptimal rewardagnostic exploration in reinforcement learning,” 2023.
G. Li, L. Shi, Y. Chen, Y. Chi, Y. Wei, “Settling the sample complexity of modelbased offline reinforcement learning,” accepted to Annals of Statistics, 2023+.
G. Li, Y. Chi, Y. Wei, Y. Chen, “Minimaxoptimal multiagent RL in Markov games with a generative model,” NeurIPS 2022 (selected as oral).
G. Li, Y. Wei, Y. Chi, Y. Chen, “Softmax policy gradient methods can take exponential time to converge,” Mathematical Programming, vol. 201, pp. 707802, 2023 (appeared in part to COLT 2021). [ArXiv][MP version][slides]
G. Li, C. Cai, Y. Chen, Y. Wei, Y. Chi, “Is QLearning minimax optimal? A tight sample complexity analysis,” accepted to Operations Research, 2023+ (appeared 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,” Operations Research, vol. 70, no. 4, pp. 2563–2578, 2022 (INFORMS George Nicholson award finalist, 2021). [ArXiv][OR version][slides]
G. Li, Y. Wei, Y. Chi, Y. Chen, “Breaking the sample size barrier in modelbased reinforcement learning with a generative model,” accepted to Operations Research, 2023+ (appeared in part to NeurIPS 2020). [paper][slides]
Spectral methods
Y. Zhou, Y. Chen, “Deflated HeteroPCA: Overcoming the curse of illconditioning in heteroskedastic PCA,” 2023. [ArXiv][slides]
Y. Yan, Y. Chen, J. Fan, “Inference for heteroskedastic PCA with missing data,” 2021. [ArXiv][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. 944967, 2021. [ArXiv][AoS version]
Y. Chen, C. Cheng, J. Fan, “Asymmetry helps: Eigenvalue and eigenvector analyses of asymmetrically perturbed lowrank matrices,” Annals of Statistics, vol. 49, no. 1, pp. 435458, 2021. [ArXiv][AoS version][slides]
Y. Chen, J. Fan, C. Ma, K. Wang, “Spectral method and regularized MLE are both optimal for topK ranking,” Annals of Statistics, vol. 47, no. 4, pp. 22042235, August 2019. [ArXiv][AoS version][slides]
