Scholarlink

<p>Many practical optimization problems lack strong convexity. Fortunately, recent studies have revealed that first-order algorithms also enjoy linear convergences under various weaker regularity conditions. While the relationship among different conditions for convex and smooth functions is well-understood, it is not the case for the nonsmooth setting. In this paper, we go beyond convexity and smoothness, and clarify the connections among common regularity conditions in the class of weakly convex functions, including <i>strong convexity</i>, <i>restricted secant inequality</i>, <i>subdifferential error bound</i>, <i>Polyak-Łojasiewicz inequality</i>, and <i>quadratic growth</i>. In addition, using these regularity conditions, we present a simple and modular proof for the linear convergence of proximal point method (PPM) for convex and weakly convex optimization problems. The linear convergence also holds when the subproblems of PPM are solved inexactly with a proper control of inexactness.</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

Error bounds, PL condition, and quadratic growth for weakly convex functions, and linear convergences of proximal point methods

  • 期刊论文

  • 发表日期：

    2026年1月9日

查看全文
  • Feng-Yi Liao,
  • Lijun Ding,
  • Yang Zheng

摘要

Many practical optimization problems lack strong convexity. Fortunately, recent studies have revealed that first-order algorithms also enjoy linear convergences under various weaker regularity conditions. While the relationship among different conditions for convex and smooth functions is well-understood, it is not the case for the nonsmooth setting. In this paper, we go beyond convexity and smoothness, and clarify the connections among common regularity conditions in the class of weakly convex functions, including strong convexity, restricted secant inequality, subdifferential error bound, Polyak-Łojasiewicz inequality, and quadratic growth. In addition, using these regularity conditions, we present a simple and modular proof for the linear convergence of proximal point method (PPM) for convex and weakly convex optimization problems. The linear convergence also holds when the subproblems of PPM are solved inexactly with a proper control of inexactness.