Decentralized Parameter-Free Online Learning
Machine Learning
2025-10-20 v1 Signal Processing
Optimization and Control
Abstract
We propose the first parameter-free decentralized online learning algorithms with network regret guarantees, which achieve sublinear regret without requiring hyperparameter tuning. This family of algorithms connects multi-agent coin-betting and decentralized online learning via gossip steps. To enable our decentralized analysis, we introduce a novel "betting function" formulation for coin-betting that simplifies the multi-agent regret analysis. Our analysis shows sublinear network regret bounds and is validated through experiments on synthetic and real datasets. This family of algorithms is applicable to distributed sensing, decentralized optimization, and collaborative ML applications.
Keywords
Cite
@article{arxiv.2510.15644,
title = {Decentralized Parameter-Free Online Learning},
author = {Tomas Ortega and Hamid Jafarkhani},
journal= {arXiv preprint arXiv:2510.15644},
year = {2025}
}