inexact proximal-gradient method

A first-order method for nonconvex-nonconcave minimax problems under a local Kurdyka-Łojasiewicz condition

  • Zhaosong Lu
  • Xiangyuan Wang
    • Categories Convex and Nonsmooth Optimization, Nonlinear Optimization, Other Topics Tags , , , ,

    We study a class of nonconvex–nonconcave minimax problems in which the inner maximization problem satisfies a local Kurdyka–Łojasiewicz (KL) condition that may vary with the outer minimization variable. In contrast to the global KL or Polyak–Łojasiewicz (PL) conditions commonly assumed in the literature—which are significantly stronger and often too restrictive in practice—this local KL condition … Read more

    Inexact Proximal-Gradient Methods with Support Identification

  • Yutong Dai
  • Daniel P. Robinson
    • Categories Convex and Nonsmooth Optimization, Data Science Algorithms Tags , , , ,

    We consider the proximal-gradient method for minimizing an objective function that is the sum of a smooth function and a non-smooth convex function. A feature that distinguishes our work from most in the literature is that we assume that the associated proximal operator does not admit a closed-form solution. To address this challenge, we study … Read more