Scholarlink

<p>We propose a simple proof of the worst-case iteration complexity for the Difference of Convex functions Algorithm <Emphasis FontCategory="SansSerif">DCA</Emphasis> for unconstrained minimization, showing that the global rate of convergence of the norm of the objective function’s gradients at the iterates converge to zero like <i>o</i>(1/<i>k</i>). A small example is also provided indicating that the rate cannot be improved.</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

Iteration complexity of the difference-of-convex algorithm for unconstrained optimization: a simple proof

  • 期刊论文

  • 发表日期：

    2026年7月20日

查看全文
  • S. Gratton,
  • Ph. L. Toint

摘要

We propose a simple proof of the worst-case iteration complexity for the Difference of Convex functions Algorithm DCA for unconstrained minimization, showing that the global rate of convergence of the norm of the objective function’s gradients at the iterates converge to zero like o(1/k). A small example is also provided indicating that the rate cannot be improved.