Emergent Mind
Stochastic subgradient method converges at the rate $O(k^{-1/4})$ on weakly convex functions
(1802.02988)
Published Feb 8, 2018
in
math.OC
and
cs.LG
Abstract
We prove that the proximal stochastic subgradient method, applied to a weakly convex problem, drives the gradient of the Moreau envelope to zero at the rate $O(k{-1/4})$. As a consequence, we resolve an open question on the convergence rate of the proximal stochastic gradient method for minimizing the sum of a smooth nonconvex function and a convex proximable function.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.