Ruinan Jin

NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration

TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD

The Implicit Bias of Stochastic AdaGrad-Norm on Separable Data

Asymptotic Convergence of SGD in Non-Convex Problems: A Stopping Times Method with Relaxed Step-size Conditions

On last-iterate convergence of distributed Stochastic Gradient Descent algorithm with momentum

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with Stochastic Gradient Descent