Fast convergence of stochastic subgradient method under interpolation

ICLR 2021  ·  Huang Fang, Zhenan Fan, Michael Friedlander ·

This paper studies the behaviour of the stochastic subgradient descent (SSGD) method applied to over-parameterized nonsmooth optimization problems that satisfy an interpolation condition. By leveraging the composite structure of the empirical risk minimization problems. We prove that SSGD converges, respectively, with rates $O(1/\epsilon)$ and $O(\log(1/\epsilon))$ for convex and strongly-convex objectives when interpolation holds. These rates coincide with established rates for the stochastic gradient descent (SGD) method applied to smooth problems that also satisfy an interpolation condition. Our analysis provides a partial explanation for the empirical observation that sometimes SGD and SSGD behave similarly for training smooth and nonsmooth machine learning models. We also prove that the rate $O(1/\epsilon)$ is optimal for the subgradient method in the convex and interpolation setting.

PDF Abstract
No code implementations yet. Submit your code now

Tasks


Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods