3 papers
cs.LG2026
Improved Bounds for Private and Robust Alignment
Wenqian Weng, Yi He, Xingyu Zhou
In this paper, we study the private and robust alignment of language models from a theoretical perspective by establishing upper bounds on the suboptimality gap in both offline and…
cs.LG2026
On the Sample Complexity of Differentially Private Policy Optimization
Yi He, Xingyu Zhou
Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning robotics, healthcare, and large language model training. The inc…
cs.LG2026
Towards Differentially Private Reinforcement Learning with General Function Approximation
Yi He, Xingyu Zhou
We present the first theoretical guarantees for differentially private online reinforcement learning (RL) with general function approximation, extending beyond prior work restricte…