Score: 0

Decentralized Parameter-Free Online Learning

Published: October 17, 2025 | arXiv ID: 2510.15644v1

By: Tomas Ortega, Hamid Jafarkhani

Potential Business Impact:

Computers learn together without needing perfect settings.

Business Areas:
MOOC Education, Software

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.

Country of Origin
🇺🇸 United States

Page Count
13 pages

Category
Computer Science:
Machine Learning (CS)