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. 2205.12751
22
5

Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization

25 May 2022
Benjamin Dubois-Taine
Francis R. Bach
Quentin Berthet
Adrien B. Taylor
ArXivPDFHTML
Abstract

We consider the problem of minimizing the sum of two convex functions. One of those functions has Lipschitz-continuous gradients, and can be accessed via stochastic oracles, whereas the other is "simple". We provide a Bregman-type algorithm with accelerated convergence in function values to a ball containing the minimum. The radius of this ball depends on problem-dependent constants, including the variance of the stochastic oracle. We further show that this algorithmic setup naturally leads to a variant of Frank-Wolfe achieving acceleration under parallelization. More precisely, when minimizing a smooth convex function on a bounded domain, we show that one can achieve an ϵ\epsilonϵ primal-dual gap (in expectation) in O~(1/ϵ)\tilde{O}(1/ \sqrt{\epsilon})O~(1/ϵ​) iterations, by only accessing gradients of the original function and a linear maximization oracle with O(1/ϵ)O(1/\sqrt{\epsilon})O(1/ϵ​) computing units in parallel. We illustrate this fast convergence on synthetic numerical experiments.

View on arXiv
Comments on this paper