collaborators

6 papers

cs.LG2025

Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

Yurun Yuan, Fan Chen, Zeyu Jia +2

Policy-based methods currently dominate reinforcement learning (RL) pipelines for large language model (LLM) reasoning, leaving value-based approaches largely unexplored. We revisi…

stat.ML2025

A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity

Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin

We study gapped scale-sensitive dimensions of a function class in both sequential and non-sequential settings. We demonstrate that covering numbers for any uniformly bounded class…

cs.LG2025

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits

Fan Chen, Zeyu Jia, Alexander Rakhlin +1

Reinforcement learning with outcome-based feedback faces a fundamental challenge: when rewards are only observed at trajectory endpoints, how do we assign credit to the right actio…

cs.LG2025

Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective

Zeyu Jia, Alexander Rakhlin, Tengyang Xie

As large language models have evolved, it has become crucial to distinguish between process supervision and outcome supervision -- two key reinforcement learning approaches to comp…

cs.LG2025

On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy

Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin

We study the problem of sequential probability assignment under logarithmic loss, both with and without side information. Our objective is to analyze the minimax regret -- a notion…

cs.LG2024

How Does Variance Shape the Regret in Contextual Bandits?

Zeyu Jia, Jian Qian, Alexander Rakhlin +1

We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in mini…