A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin
Gaussian Sequence Model: Sample Complexities of Testing, Estimation and LFHT Zeyu Jia, Yury Polyanskiy
(* denote alphabetical order)
Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits Fan Chen*, Zeyu Jia*, Alexander Rakhlin*, Tengyang Xie* Neural Information Processing Systems (NeurIPS) 2025
Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning Yurun Yuan, Fan Chen, Zeyu Jia, Alexander Rakhlin, Tengyang Xie Neural Information Processing Systems (NeurIPS) 2025
Rate of convergence of the smoothed empirical Wasserstein distance Adam Block*, Zeyu Jia*, Yury Polyanskiy*, Alexander Rakhlin* To Appear in Annales de l'Institut Henri Poincaré
On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin Conference on Learning Theory (COLT) 2025
Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective Zeyu Jia, Alexander Rakhlin, Tengyang Xie International Conference on Machine Learning (ICML) 2025
How Does Variance Shape the Regret in Contextual Bandits? Zeyu Jia*, Jian Qian*, Alexander Rakhlin*, Chen-Yu Wei* Neural Information Processing Systems (NeurIPS) 2024
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data Zeyu Jia*, Alexander Rakhlin*, Ayush Sekhari*, Chen-Yu Wei* Conference on Learning Theory (COLT) 2024
When is Agnostic Reinforcement Learning Statistically Tractable? Zeyu Jia*, Gene Li*, Alexander Rakhlin*, Ayush Sekhari*, Nathan Srebro* Neural Information Processing Systems (NeurIPS) 2023
Entropic characterization of optimal rates for learning Gaussian mixtures Zeyu Jia, Yury Polyanskiy, Yihong Wu Conference on Learning Theory (COLT) 2023
Linear Reinforcement Learning with Ball Structure Action Space Zeyu Jia, Randy Jia, Dhruv Madeka, Dean P Foster Algorithmic Learning Theory (ALT) 2023
Intrinsic Dimension Estimation Using Wasserstein Distance Adam Block*, Zeyu Jia*, Yury Polyanskiy*, Alexander Rakhlin* Journal of Machine Learning Research (JMLR) 2022
Search Direction Correction with Normalized Gradient Makes First-Order Methods Faster Yifei Wang, Zeyu Jia, Zaiwen Wen Journal of Scientific Computing 2022
Minimax-optimal off-policy evaluation with linear function approximation Yaqi Duan*, Zeyu Jia*, Mengdi Wang* International Conference on Machine Learning (ICML) 2020
Model-Based Reinforcement Learning with Value-Targeted Regression Alex Ayoub*, Zeyu Jia*, Csaba Szepesvari*, Mengdi Wang*, Lin Yang* International Conference on Machine Learning (ICML) 2020
Feature-based q-learning for two-player stochastic games Zeyu Jia, Lin F Yang, Mengdi Wang Optimization Foundations for Reinforcement Learning Workshop at NeurIPS 2019