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

2024/10/07 by Yong Xia, Xia, Yong, Yanhao Zhang +3 · 1 citation
Mathematics · #90C25 #90C30 #Advanced Optimization Algorithms Research #FOS: Mathematics #Iterative Methods for Nonlinear Equations #Numerical methods in inverse problems #Optimization and Control (math.OC)

paper · pdf · doi:10.48550/arxiv.2410.22336

openalex publication_date 2024/10/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Lipschitz-Free Mirror Descent Methods for Non-Smooth Optimization Problems

Related

• Convergence Rates for Deterministic and Stochastic Subgradient Methods Without Lipschitz Continuity
• Exact Convergence rate of the subgradient method by using Polyak step size
• Projection Efficient Subgradient Method and Optimal Nonsmooth Frank-Wolfe Method
• Sufficient conditions for instability of the subgradient method with constant step size
• Examples of pathological dynamics of the subgradient method for Lipschitz path-differentiable functions