Online Learning with Adversaries: A Differential-Inclusion Analysis - IMT Atlantique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Online Learning with Adversaries: A Differential-Inclusion Analysis

Résumé

We introduce an observation-matrix-based framework for fully asynchronous online Federated Learning (FL) with adversaries. In this work, we demonstrate its effectiveness in estimating the mean of a random vector. Our main result is that the proposed algorithm almost surely converges to the desired mean μ . This makes ours the first asynchronous FL method to have an a.s. convergence guarantee in the presence of adversaries. We derive this convergence using a novel differential-inclusion-based two-timescale analysis. Two other highlights of our proof include (a) the use of a novel Lyapunov function to show that μ is the unique global attractor for our algorithm's limiting dynamics, and (b) the use of martingale and stopping-time theory to show that our algorithm's iterates are almost surely bounded.

Dates et versions

hal-04594622 , version 1 (30-05-2024)

Identifiants

Citer

Swetha Ganesh, Alexandre Reiffers-Masson, Gugan Thoppe. Online Learning with Adversaries: A Differential-Inclusion Analysis. CDC 2023: 62nd IEEE Conference on Decision and Control, Dec 2023, Singapore, Singapore. pp.1288-1293, ⟨10.1109/CDC49753.2023.10384052⟩. ⟨hal-04594622⟩
14 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More