Work

Learning-Augmented Decentralized Online Convex Optimization in Networks

Year: 2025

Type: article

Abstract: This paper studies learning-augmented decentralized online convex optimization in a networked multi-agent system, a challenging setting that has remained under-explored. We first consider a linear learning-augmented decentralized online algorithm (LADO-Lin) that combines a machine learning (ML) policy with a baseline expert policy in a linear manner. We show that, while LADO-Lin can exploit the potential of ML predictions to improve the average cost performance, it cannot have guaranteed worst-case performance. To address this limitation, we propose a novel online algorithm (LADO) that adaptively combines the ML policy and expert policy to safeguard the ML predictions to achieve strong competitiveness guarantees. We also prove the average cost bound for LADO, revealing the tradeoff between average performance and worst-case robustness and demonstrating the advantage of training the ML policy by explicitly considering the robustness requirement. Finally, we run an experiment on decentralized battery management. Our results highlight the potential of ML augmentation to improve the average performance as well as the guaranteed worst-case performance of LADO.

Source: ACM SIGMETRICS Performance Evaluation Review

DOI: 10.1145/3744970.3727293

Authors: Pengfei Li, Jianyi Yang, Adam Wierman, Shaolei Ren

Institutions: University of California, Riverside, University of Houston, California Institute of Technology

Language: English

Topic: Optimization and Search Problems

Subfield: Computer Networks and Communications

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: National Science Foundation, Resnick Sustainability Institute for Science, Energy and Sustainability, California Institute of Technology, Universitas Brawijaya