Stochastic subgradient method converges at the rate (k^{-1/4})$ on weakly convex function

  • Damek Davis
  • Dmitriy Drusvyatskiy
    • Categories Nonsmooth Optimization Tags , , Short URL: https://optimization-online.org/?p=15029

    We prove that the projected stochastic subgradient method, applied to a weakly convex problem, drives the gradient of the Moreau envelope to zero at the rate $O(k^{-1/4})$.

    Article

    Download

    View PDF