Adaptive Sample Sharing for Multi Agent Linear Bandits
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909624202952704 |
|---|---|
| author | Cherkaoui, Hamza Barlier, Merwan Colin, Igor |
| author_facet | Cherkaoui, Hamza Barlier, Merwan Colin, Igor |
| contents | The multi-agent linear bandit setting is a well-known setting for which designing efficient collaboration between agents remains challenging. This paper studies the impact of data sharing among agents on regret minimization. Unlike most existing approaches, our contribution does not rely on any assumptions on the bandit parameters structure. Our main result formalizes the trade-off between the bias and uncertainty of the bandit parameter estimation for efficient collaboration. This result is the cornerstone of the Bandit Adaptive Sample Sharing (BASS) algorithm, whose efficiency over the current state-of-the-art is validated through both theoretical analysis and empirical evaluations on both synthetic and real-world datasets. Furthermore, we demonstrate that, when agents' parameters display a cluster structure, our algorithm accurately recovers them. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_08710 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Adaptive Sample Sharing for Multi Agent Linear Bandits Cherkaoui, Hamza Barlier, Merwan Colin, Igor Machine Learning The multi-agent linear bandit setting is a well-known setting for which designing efficient collaboration between agents remains challenging. This paper studies the impact of data sharing among agents on regret minimization. Unlike most existing approaches, our contribution does not rely on any assumptions on the bandit parameters structure. Our main result formalizes the trade-off between the bias and uncertainty of the bandit parameter estimation for efficient collaboration. This result is the cornerstone of the Bandit Adaptive Sample Sharing (BASS) algorithm, whose efficiency over the current state-of-the-art is validated through both theoretical analysis and empirical evaluations on both synthetic and real-world datasets. Furthermore, we demonstrate that, when agents' parameters display a cluster structure, our algorithm accurately recovers them. |
| title | Adaptive Sample Sharing for Multi Agent Linear Bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2309.08710 |