Optimal Thresholding Linear Bandit
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909106991792128 |
|---|---|
| author | Rivera, Eduardo Ochoa Tewari, Ambuj |
| author_facet | Rivera, Eduardo Ochoa Tewari, Ambuj |
| contents | We study a novel pure exploration problem: the $ε$-Thresholding Bandit Problem (TBP) with fixed confidence in stochastic linear bandits. We prove a lower bound for the sample complexity and extend an algorithm designed for Best Arm Identification in the linear case to TBP that is asymptotically optimal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09467 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimal Thresholding Linear Bandit Rivera, Eduardo Ochoa Tewari, Ambuj Machine Learning We study a novel pure exploration problem: the $ε$-Thresholding Bandit Problem (TBP) with fixed confidence in stochastic linear bandits. We prove a lower bound for the sample complexity and extend an algorithm designed for Best Arm Identification in the linear case to TBP that is asymptotically optimal. |
| title | Optimal Thresholding Linear Bandit |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2402.09467 |