Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914967063625728 |
|---|---|
| author | Zhang, Raymond Combes, Richard |
| author_facet | Zhang, Raymond Combes, Richard |
| contents | We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the "mismatched sampling paradox": A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior. The code used to generate the experiments is available at https://github.com/RaymZhang/CTS-Mismatched-Paradox |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_05441 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox Zhang, Raymond Combes, Richard Machine Learning We consider Thompson Sampling (TS) for linear combinatorial semi-bandits and subgaussian rewards. We propose the first known TS whose finite-time regret does not scale exponentially with the dimension of the problem. We further show the "mismatched sampling paradox": A learner who knows the rewards distributions and samples from the correct posterior distribution can perform exponentially worse than a learner who does not know the rewards and simply samples from a well-chosen Gaussian posterior. The code used to generate the experiments is available at https://github.com/RaymZhang/CTS-Mismatched-Paradox |
| title | Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.05441 |