2 papers
math.NA2026
Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
Jianfeng Lu, Yinchen Luo
Let on , where is -strongly convex and -smooth, and denote by the condition number. We consider windowed thinning, an exact si…
cs.LG2025
Periodic Asynchrony: An On-Policy Approach for Accelerating LLM Reinforcement Learning
Jian Lu, Yi Luo
Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical chall…