Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation

Alexandre Reiffers-Masson 1, 2 Isabel Amigo 1, 2 
2 Lab-STICC_MATHNET - Equipe Math & Net
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance : UMR6285
Abstract : 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

https://hal-imt-atlantique.archives-ouvertes.fr/hal-03770518
Contributor : Alexandre Reiffers-Masson Connect in order to contact the contributor
Submitted on : Thursday, September 29, 2022 - 8:14:36 AM
Last modification on : Sunday, October 2, 2022 - 3:44:02 AM

Identifiers

Citation

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

Share

Metrics

Record views

9

Files downloads

4