pith. sign in

arxiv: 1802.02988 · v3 · pith:BFXHJX6Pnew · submitted 2018-02-08 · 🧮 math.OC · cs.LG

Stochastic subgradient method converges at the rate O(k^(-1/4)) on weakly convex functions

classification 🧮 math.OC cs.LG
keywords convexmethodratestochasticfunctiongradientproximalsubgradient
0
0 comments X
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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. The Measure of Deception: An Analysis of Data Forging in Machine Unlearning

    cs.LG 2025-09 conditional novelty 8.0

    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.

  2. Restart and Adaptive Acceleration in Stochastic Gradient Methods

    math.OC 2026-06 conditional novelty 5.0

    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.