English

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

Optimization and Control 2024-11-26 v3 Machine Learning

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\epsilon primal-dual gap (in expectation) in O~(1/ϵ)\tilde{O}(1/ \sqrt{\epsilon}) iterations, by only accessing gradients of the original function and a linear maximization oracle with O(1/ϵ)O(1/\sqrt{\epsilon}) computing units in parallel. We illustrate this fast convergence on synthetic numerical experiments.

Keywords

Cite

@article{arxiv.2205.12751,
  title  = {Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization},
  author = {Benjamin Dubois-Taine and Francis Bach and Quentin Berthet and Adrien Taylor},
  journal= {arXiv preprint arXiv:2205.12751},
  year   = {2024}
}
R2 v1 2026-06-24T11:28:22.702Z