Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.01425 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916595223232512 |
|---|---|
| author | Tuynman, Adrienne Degenne, Rémy |
| author_facet | Tuynman, Adrienne Degenne, Rémy |
| contents | In a fixed-confidence pure exploration problem in stochastic multi-armed bandits, an algorithm iteratively samples arms and should stop as early as possible and return the correct answer to a query about the arms distributions. We are interested in batched methods, which change their sampling behaviour only a few times, between batches of observations. We give an instance-dependent lower bound on the number of batches used by any sample efficient algorithm for any pure exploration task. We then give a general batched algorithm and prove upper bounds on its expected sample complexity and batch complexity. We illustrate both lower and upper bounds on best-arm identification and thresholding bandits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01425 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Batch Complexity of Bandit Pure Exploration Tuynman, Adrienne Degenne, Rémy Machine Learning In a fixed-confidence pure exploration problem in stochastic multi-armed bandits, an algorithm iteratively samples arms and should stop as early as possible and return the correct answer to a query about the arms distributions. We are interested in batched methods, which change their sampling behaviour only a few times, between batches of observations. We give an instance-dependent lower bound on the number of batches used by any sample efficient algorithm for any pure exploration task. We then give a general batched algorithm and prove upper bounds on its expected sample complexity and batch complexity. We illustrate both lower and upper bounds on best-arm identification and thresholding bandits. |
| title | The Batch Complexity of Bandit Pure Exploration |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.01425 |