Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

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

Résumé

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

Dates et versions

hal-03769647 , version 1 (05-09-2022)

Identifiants

Citer

Benjamin Dubois-Taine, Francis Bach, Quentin Berthet, Adrien Taylor. Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization. 2022. ⟨hal-03769647⟩
18 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More