ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1907.04232
10
112

Unified Optimal Analysis of the (Stochastic) Gradient Method

9 July 2019
Sebastian U. Stich
ArXivPDFHTML
Abstract

In this note we give a simple proof for the convergence of stochastic gradient (SGD) methods on μ\muμ-convex functions under a (milder than standard) LLL-smoothness assumption. We show that for carefully chosen stepsizes SGD converges after TTT iterations as O(LR2exp⁡[−μ4LT]+σ2μT)O\left( LR^2 \exp \bigl[-\frac{\mu}{4L}T\bigr] + \frac{\sigma^2}{\mu T} \right)O(LR2exp[−4Lμ​T]+μTσ2​) where σ2\sigma^2σ2 measures the variance in the stochastic noise. For deterministic gradient descent (GD) and SGD in the interpolation setting we have σ2=0\sigma^2 =0σ2=0 and we recover the exponential convergence rate. The bound matches with the best known iteration complexity of GD and SGD, up to constants.

View on arXiv
Comments on this paper