Decentralized Parameter-Free Online Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911216707829760 |
|---|---|
| author | Ortega, Tomas Jafarkhani, Hamid |
| author_facet | Ortega, Tomas Jafarkhani, Hamid |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15644 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decentralized Parameter-Free Online Learning Ortega, Tomas Jafarkhani, Hamid Machine Learning Signal Processing Optimization and Control 68W10, 68W15, 68W40, 90C06, 90C35, 90C26 G.1.6; F.2.1; E.4 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. |
| title | Decentralized Parameter-Free Online Learning |
| topic | Machine Learning Signal Processing Optimization and Control 68W10, 68W15, 68W40, 90C06, 90C35, 90C26 G.1.6; F.2.1; E.4 |
| url | https://arxiv.org/abs/2510.15644 |