Sequential stochastic blackbox optimization with zeroth order gradient estimators - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Sequential stochastic blackbox optimization with zeroth order gradient estimators

Résumé

This workconsiders stochastic optimization problems in which the objective function values can only be computed by a blackbox corrupted by some random noise following an unknown distribution. The proposed method is based on sequential stochastic optimization (SSO): the original problem is decomposed into a sequence of subproblems. Each of these subproblems is solved using a zeroth order version of a sign stochastic gradient descent with momentum algorithm (ZO-Signum) and with an increasingly fine precision. This decomposition allows a good exploration of the space while maintaining the efficiency of the algorithm once it gets close to the solution. Under Lipschitz continuity assumption on the blackbox, a convergence rate in expectation is derived for the ZO-signum algorithm. Moreover, if the blackbox is smooth and convex or locally convex around its minima, a convergence rate to an epsilon-optimal point of the problem may be obtained for the SSO algorithm. Numerical experiments are conducted to compare the SSO algorithm with other state-of-the-art algorithms and to demonstrate its competitiveness.
Fichier non déposé

Dates et versions

hal-04684482 , version 1 (02-09-2024)

Identifiants

  • HAL Id : hal-04684482 , version 1

Citer

Jean Bigeon, Charles Audet, Romain Couderc, Michael Kokkolaras. Sequential stochastic blackbox optimization with zeroth order gradient estimators. MOPTA 2023, Lehigh University Bethlehem, PA USA, Aug 2023, Bethlehem, PA, USA, United States. ⟨hal-04684482⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More