Scholarlink

<p>This paper develops a comprehensive convergence analysis for generic classes of descent algorithms in nonsmooth and nonconvex optimization under several conditions of the Polyak-Łojasiewicz-Kurdyka (PLK) type. Along other results, we prove the finite termination of generic algorithms under the PLK conditions with lower exponents. Specifications are given to establish new convergence rates for inexact reduced gradient methods and some versions of the boosted algorithm in DC programming. It is revealed, e.g., that the lower exponent PLK conditions for a broad class of difference programs are incompatible with the gradient Lipschitz continuity for the plus function around a local minimizer. On the other hand, we show that the above inconsistency observation may fail if the Lipschitz continuity is replaced by merely the gradient continuity.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Convergence of Descent Optimization Algorithms under Polyak-Łojasiewicz-Kurdyka Conditions

  • 期刊论文

  • 发表日期：

    2025年8月11日

查看全文
  • Glaydston Bento,
  • Boris Mordukhovich,
  • Tiago Mota,
  • Yurii Nesterov

摘要

This paper develops a comprehensive convergence analysis for generic classes of descent algorithms in nonsmooth and nonconvex optimization under several conditions of the Polyak-Łojasiewicz-Kurdyka (PLK) type. Along other results, we prove the finite termination of generic algorithms under the PLK conditions with lower exponents. Specifications are given to establish new convergence rates for inexact reduced gradient methods and some versions of the boosted algorithm in DC programming. It is revealed, e.g., that the lower exponent PLK conditions for a broad class of difference programs are incompatible with the gradient Lipschitz continuity for the plus function around a local minimizer. On the other hand, we show that the above inconsistency observation may fail if the Lipschitz continuity is replaced by merely the gradient continuity.