Stochastic subgradient method converges at the rate O(k^(-1/4)) on weakly convex functions
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
The Measure of Deception: An Analysis of Data Forging in Machine Unlearning
The Lebesgue measure of ε-forging sets decays as O(ε) or ε^d for linear models and as ε^{(d-r)/2} under mild regularity assumptions, with vanishing probability of random sampling.
-
Restart and Adaptive Acceleration in Stochastic Gradient Methods
Restart schemes for SGD on KL-satisfying non-smooth weakly convex problems deliver accelerated convergence robust to exponent misspecification, with optimal schedules resembling Polyak steps.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.