3 papers
cs.LG2024
Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
Dongxie Wen, Hanyan Yin, Xiao Zhang +3
Linear bandits have become a cornerstone of online learning and sequential decision-making, providing solid theoretical foundations for balancing exploration and exploitation. With…
cs.LG2024
Universal Online Convex Optimization with Projection per Round
Wenhao Yang, Yibo Wang, Peng Zhao +1
To address the uncertainty in function types, recent progress in online convex optimization (OCO) has spurred the development of universal algorithms that simultaneously attain min…
cs.LG2023
Stochastic Approximation Approaches to Group Distributionally Robust Optimization and Beyond
Lijun Zhang, Haomin Bai, Peng Zhao +2
This paper investigates group distributionally robust optimization (GDRO) with the goal of learning a model that performs well over different distributions. First, we formulate…