Robust Online Learning Over Networks

• 成果类型: Article
• 署名作者: Bastianello, Nicola; Deplano, Diego; Franceschelli, Mauro; Johansson, Karl H.
• 署名单位: Royal Institute of Technology; University of Cagliari
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2024.3441723
• 发表日期: 2025
• 页码: 933-946
• 关键词: Measurement; CONVERGENCE; computational modeling; training; Distributed databases; Robustness; Numerical models; Asynchronous networks; Distributed Learning; online learning; unreliable communications

摘要

The recent deployment of multiagent 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: 1) online training, i.e., the local data change over time; 2) asynchronous agent computations; 3) unreliable and limited communications; and 4) 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 1)-4). 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 1)-4).