Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912345389793280 |
|---|---|
| author | Nguyen, Nicolas Aouali, Imad György, András Vernade, Claire |
| author_facet | Nguyen, Nicolas Aouali, Imad György, András Vernade, Claire |
| contents | We study the problem of Bayesian fixed-budget best-arm identification (BAI) in structured bandits. We propose an algorithm that uses fixed allocations based on the prior information and the structure of the environment. We provide theoretical bounds on its performance across diverse models, including the first prior-dependent upper bounds for linear and hierarchical BAI. Our key contribution is introducing new proof methods that result in tighter bounds for multi-armed BAI compared to existing methods. We extensively compare our approach to other fixed-budget BAI methods, demonstrating its consistent and robust performance in various settings. Our work improves our understanding of Bayesian fixed-budget BAI in structured bandits and highlights the effectiveness of our approach in practical scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05878 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits Nguyen, Nicolas Aouali, Imad György, András Vernade, Claire Machine Learning We study the problem of Bayesian fixed-budget best-arm identification (BAI) in structured bandits. We propose an algorithm that uses fixed allocations based on the prior information and the structure of the environment. We provide theoretical bounds on its performance across diverse models, including the first prior-dependent upper bounds for linear and hierarchical BAI. Our key contribution is introducing new proof methods that result in tighter bounds for multi-armed BAI compared to existing methods. We extensively compare our approach to other fixed-budget BAI methods, demonstrating its consistent and robust performance in various settings. Our work improves our understanding of Bayesian fixed-budget BAI in structured bandits and highlights the effectiveness of our approach in practical scenarios. |
| title | Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.05878 |