Robust Online Learning over Networks
arXiv:2309.00520 · doi:10.1109/TAC.2024.3441723
Abstract
The recent deployment of multi-agent networks has enabled the distributed solution of learning problems, where agents cooperate to train a global model without sharing their local, private data. This work specifically targets some prevalent challenges inherent to distributed learning: (i) online training, i.e., the local data change over time; (ii) asynchronous agent computations; (iii) unreliable and limited communications; and (iv) inexact local computations. To tackle these challenges, we apply the Distributed Operator Theoretical (DOT) version of the Alternating Direction Method of Multipliers (ADMM), which we call "DOT-ADMM". We prove that if the DOT-ADMM operator is metric subregular, then it converges with a linear rate for a large class of (not necessarily strongly) convex learning problems toward a bounded neighborhood of the optimal time-varying solution, and characterize how such neighborhood depends on (i)-(iv). We first derive an easy-to-verify condition for ensuring the metric subregularity of an operator, followed by tutorial examples on linear and logistic regression problems. We corroborate the theoretical analysis with numerical simulations comparing DOT-ADMM with other state-of-the-art algorithms, showing that only the proposed algorithm exhibits robustness to (i)-(iv).
References in corpus (14)
- ARock: an Algorithmic Framework for Asynchronous Parallel Coordinate Updates
- Asynchronous Distributed ADMM for Large-Scale Optimization- Part I: Algorithm and Convergence Analysis
- Federated Learning: A Signal Processing Perspective
- Distributed Optimization for Smart Cyber-Physical Networks
- Asynchronous Distributed Optimization over Lossy Networks via Relaxed ADMM: Stability and Linear Convergence
- Optimization and Learning with Information Streams: Time-varying Algorithms and Applications
- Coordinate Friendly Structures, Algorithms and Applications
- Dynamic Max-Consensus and Size Estimation of Anonymous Multi-Agent Networks
- Analysis of Distributed ADMM Algorithm for Consensus Optimization in Presence of Node Error
- Can Primal Methods Outperform Primal-dual Methods in Decentralized Dynamic Optimization?
- Distributed and Inexact Proximal Gradient Method for Online Convex Optimization
- Distributed estimation and control of node centrality in undirected asymmetric networks
- Novel Stability Conditions for Nonlinear Monotone Systems and Consensus in Multi-Agent Networks
- A Stochastic Operator Framework for Optimization and Learning with Sub-Weibull Errors