3 papers
math.OC2024
Zeroth-Order Katyusha: An Accelerated Derivative-Free Method for Composite Convex Optimization
Silan Zhang, Yujie Tang
We investigate accelerated zeroth-order algorithms for smooth composite convex optimization problems. While for unconstrained optimization, existing methods that merge 2-point zero…
math.OC2024
Benign Nonconvex Landscapes in Optimal and Robust Control, Part II: Extended Convex Lifting
Yang Zheng, Chih-Fan Pai, Yujie Tang
Many optimal and robust control problems are nonconvex and potentially nonsmooth in their policy optimization forms. In Part II of this paper, we introduce a new and unified Extend…
math.OC2023
On the Global Optimality of Direct Policy Search for Nonsmooth Output-Feedback Control
Yujie Tang, Yang Zheng
Direct policy search has achieved great empirical success in reinforcement learning. Recently, there has been increasing interest in studying its theoretical properties for continu…