3 papers
math.OC2026
Value Mirror Descent for Reinforcement Learning
Zhichao Jia, Guanghui Lan
Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL). Under a generative sampling model, these me…
math.OC2024
Nearly Optimal Risk Minimization
Zhichao Jia, Guanghui Lan, Zhe Zhang
Convex risk measures play a foundational role in the area of stochastic optimization. However, in contrast to risk neutral models, their applications are still limited due to the l…
math.OC2023
Goldstein Stationarity in Lipschitz Constrained Optimization
Benjamin Grimmer, Zhichao Jia
We prove the first convergence guarantees for a subgradient method minimizing a generic Lipschitz function over generic Lipschitz inequality constraints. No smoothness or convexity…