A Fully Stochastic Primal-Dual Algorithm - Archive ouverte HAL Access content directly
Journal Articles Optimization Letters Year : 2020

A Fully Stochastic Primal-Dual Algorithm

Abstract

A new stochastic primal-dual algorithm for solving a composite optimization problem is proposed. It is assumed that all the functions / operators that enter the optimization problem are given as statistical expectations. These expectations are unknown but revealed across time through i.i.d realizations. The proposed algorithm is proven to converge to a saddle point of the Lagrangian function. In the framework of the monotone operator theory, the convergence proof relies on recent results on the stochastic Forward Backward algorithm involving random monotone operators. An example of convex optimization under stochastic linear constraints is considered.
Fichier principal
Vignette du fichier
19fully.pdf (348.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02369882 , version 1 (19-11-2019)
hal-02369882 , version 2 (18-12-2020)

Identifiers

Cite

Pascal Bianchi, Walid Hachem, Adil Salim. A Fully Stochastic Primal-Dual Algorithm. Optimization Letters, 2020, ⟨10.1007/s11590-020-01614-y⟩. ⟨hal-02369882v2⟩
100 View
149 Download

Altmetric

Share

Gmail Facebook X LinkedIn More