Decentralized Parameter-Free Online Learning

Tomas Ortega, Hamid Jafarkhani
10/17/2025
cs.LGeess.SPmath.OC

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret

85% match2023

Efficient Methods for Non-stationary Online Learning

84% match2026

Online Learning and Equilibrium Computation with Ranking Feedback

84% match2026

Multitask Online Learning: Listen to the Neighborhood Buzz

84% match2023

On the Necessity of Collaboration for Online Model Selection with Decentralized Data

83% match2026

Impact of Decentralized Learning on Player Utilities in Stackelberg Games

83% match2026

Cite this paper

@article{ortega2025decentralized,
  title  = {Decentralized Parameter-Free Online Learning},
  author = {Tomas Ortega and Hamid Jafarkhani},
  year   = {2025},
  eprint = {2510.15644},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2510.15644v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2510.15644.svg)](https://codeofpaper.com/paper/2510.15644)

Discussion