Online Learning with Adversaries: A Differential-Inclusion Analysis

Ganesh, S and Reiffers-Masson, A and Thoppe, G (2023) Online Learning with Adversaries: A Differential-Inclusion Analysis. In: UNSPECIFIED, pp. 1288-1293.

PDF pro_iee_con_dec_con_2023 - Published Version Download (412kB)

Abstract

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. © 2023 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings of the IEEE Conference on Decision and Control
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to authors.
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	17 May 2024 04:36
Last Modified:	17 May 2024 04:36
URI:	https://eprints.iisc.ac.in/id/eprint/84550

Actions (login required)

View Item