Papers

Publications and Preprints

A complete list of current papers, with links to arXiv, proceedings, publishers, and slides where available.

Preprint

Robust average-reward Markov decision processes: minimax-optimal learning via plug-in reductions.

Yuepeng Yang, Yuxin Chen, Yuejie Chi

arXiv, 2026

arXiv

Preprint

Sample efficient inductive matrix completion with noise and inexact side information.

Yuepeng Yang, Cong Ma

arXiv, 2026

arXiv

Preprint

Estimating shared subspace with AJIVE: the power and limitation of multiple data matrices.

Yuepeng Yang, Cong Ma

arXiv, 2025

arXiv

JASA

Random pairing MLE for estimation of item parameters in Rasch model.

Yuepeng Yang, Cong Ma

Journal of the American Statistical Association, 2026

arXiv JASA

COLT 2024

Top-K ranking with monotone adversary.

Yuepeng Yang, Antares Chen, Lorenzo Orecchia, Cong Ma

Conference on Learning Theory, 2024

arXiv COLT Slides

ICLR 2023

O(T^-1) convergence of optimistic-follow-the-regularized-leader in two-player zero-sum Markov games.

Yuepeng Yang, Cong Ma

International Conference on Learning Representations, 2023

arXiv ICLR Slides

TIT 2023

Optimal tuning-free convex relaxation for noisy matrix completion.

Yuepeng Yang, Cong Ma

IEEE Transactions on Information Theory, 2023

arXiv IEEE Slides