Lipschitz-free Projected Subgradient Method with Time-varying Step-size

Yong Xia, Yanhao Zhang, Zhihan Zhu

公開日: 2024/10/7

Abstract

We introduce a novel family of time-varying step-sizes for the classical projected subgradient method, offering optimal ergodic convergence. Importantly, this approach does not depend on the Lipschitz assumption of the objective function, thereby broadening the convergence result of projected subgradient method to non-Lipschitz case.