Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation - IMT Atlantique
Pré-Publication, Document De Travail Année : 2022

Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation

Résumé

In this paper, we propose an iterative scheme for distributed Byzantineresilient estimation of a gradient associated with a black-box model. Our algorithm is based on simultaneous perturbation, secure state estimation and two-timescale stochastic approximations. We also show the performance of our algorithm through numerical experiments.
Fichier principal
Vignette du fichier
Multi_agents_optimizationByzantine(13).pdf (1.39 Mo) Télécharger le fichier

Dates et versions

hal-03770518 , version 1 (29-09-2022)

Identifiants

Citer

Alexandre Reiffers-Masson, Isabel Amigo. Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation. 2022. ⟨hal-03770518⟩
38 Consultations
79 Téléchargements

Altmetric

Partager

More