3 papers
cs.LG2025
TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback
Lei Pang, Jun Luo, Ruinan Jin
Group Relative Policy Optimization (GRPO), recently introduced by DeepSeek, is a critic-free reinforcement learning algorithm for fine-tuning large language models. GRPO replaces t…
math.OC2025
Convergence Analysis of the Last Iterate in Distributed Stochastic Gradient Descent with Momentum
Difei Cheng, Ruinan Jin, Hong Qiao +1
Distributed stochastic gradient methods are widely used to preserve data privacy and ensure scalability in large-scale learning tasks. While existing theory on distributed momentum…
cs.LG2025
Stochastic Gradient Descent in Non-Convex Problems: Asymptotic Convergence with Relaxed Step-Size via Stopping Time Methods
Ruinan Jin, Difei Cheng, Hong Qiao +3
Stochastic Gradient Descent (SGD) is widely used in machine learning research. Previous convergence analyses of SGD under the vanishing step-size setting typically require Robbins-…