MMODELYST
Papers/Decentralized Parameter-Free Online Learning with Compressed Gossip
PAP

Decentralized Parameter-Free Online Learning with Compressed Gossip

May 27, 2026

arXiv
Abstract

We study decentralized online convex optimization when agents communicate over a graph and messages may be compressed. Classical decentralized online methods typically require learning-rate choices that depend on the horizon, comparator scale, or other problem parameters, while compressed communication introduces additional disagreement that must be controlled. We propose DECO-EF (DEcentralized COin-betting with Error Feedback), a decentralized parameter-free online learning algorithm that combines coin-betting predictions with compressed difference-based gossip. Each agent maintains a clean accumulated state and a compressed tracker, and communicates only compressed state differences during gossip steps. The method is parameter-free in the online-learning sense: it does not tune to the horizon, the comparator norm, or the learning rate. We prove expected comparator-adaptive network-regret bounds for DECO-EF under compressed communication. To the best of our knowledge, this gives the first expected sublinear network-regret guarantees for parameter-free decentralized online learning under compressed communication.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Tomas Ortega, Hamid Jafarkhani
Your notes (browser-local)
saved
arXiv:2605.27831