Generalized Linear Bandits with Limited Adaptivity
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_ | 1866914116666392576 |
|---|---|
| author | Sawarni, Ayush Das, Nirjhar Barman, Siddharth Sinha, Gaurav |
| author_facet | Sawarni, Ayush Das, Nirjhar Barman, Siddharth Sinha, Gaurav |
| contents | We study the generalized linear contextual bandit problem within the constraints of limited adaptivity. In this paper, we present two algorithms, $\texttt{B-GLinCB}$ and $\texttt{RS-GLinCB}$, that address, respectively, two prevalent limited adaptivity settings. Given a budget $M$ on the number of policy updates, in the first setting, the algorithm needs to decide upfront $M$ rounds at which it will update its policy, while in the second setting it can adaptively perform $M$ policy updates during its course. For the first setting, we design an algorithm $\texttt{B-GLinCB}$, that incurs $\tilde{O}(\sqrt{T})$ regret when $M = Ω( \log{\log T} )$ and the arm feature vectors are generated stochastically. For the second setting, we design an algorithm $\texttt{RS-GLinCB}$ that updates its policy $\tilde{O}(\log^2 T)$ times and achieves a regret of $\tilde{O}(\sqrt{T})$ even when the arm feature vectors are adversarially generated. Notably, in these bounds, we manage to eliminate the dependence on a key instance dependent parameter $κ$, that captures non-linearity of the underlying reward model. Our novel approach for removing this dependence for generalized linear contextual bandits might be of independent interest. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06831 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generalized Linear Bandits with Limited Adaptivity Sawarni, Ayush Das, Nirjhar Barman, Siddharth Sinha, Gaurav Machine Learning We study the generalized linear contextual bandit problem within the constraints of limited adaptivity. In this paper, we present two algorithms, $\texttt{B-GLinCB}$ and $\texttt{RS-GLinCB}$, that address, respectively, two prevalent limited adaptivity settings. Given a budget $M$ on the number of policy updates, in the first setting, the algorithm needs to decide upfront $M$ rounds at which it will update its policy, while in the second setting it can adaptively perform $M$ policy updates during its course. For the first setting, we design an algorithm $\texttt{B-GLinCB}$, that incurs $\tilde{O}(\sqrt{T})$ regret when $M = Ω( \log{\log T} )$ and the arm feature vectors are generated stochastically. For the second setting, we design an algorithm $\texttt{RS-GLinCB}$ that updates its policy $\tilde{O}(\log^2 T)$ times and achieves a regret of $\tilde{O}(\sqrt{T})$ even when the arm feature vectors are adversarially generated. Notably, in these bounds, we manage to eliminate the dependence on a key instance dependent parameter $κ$, that captures non-linearity of the underlying reward model. Our novel approach for removing this dependence for generalized linear contextual bandits might be of independent interest. |
| title | Generalized Linear Bandits with Limited Adaptivity |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.06831 |