Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916130487009280 |
|---|---|
| author | Kuroki, Yuko Rumi, Alberto Tsuchiya, Taira Vitale, Fabio Cesa-Bianchi, Nicolò |
| author_facet | Kuroki, Yuko Rumi, Alberto Tsuchiya, Taira Vitale, Fabio Cesa-Bianchi, Nicolò |
| contents | We study best-of-both-worlds algorithms for $K$-armed linear contextual bandits. Our algorithms deliver near-optimal regret bounds in both the adversarial and stochastic regimes, without prior knowledge about the environment. In the stochastic regime, we achieve the polylogarithmic rate $\frac{(dK)^2\mathrm{poly}\log(dKT)}{Δ_{\min}}$, where $Δ_{\min}$ is the minimum suboptimality gap over the $d$-dimensional context space. In the adversarial regime, we obtain either the first-order $\widetilde{O}(dK\sqrt{L^*})$ bound, or the second-order $\widetilde{O}(dK\sqrt{Λ^*})$ bound, where $L^*$ is the cumulative loss of the best action and $Λ^*$ is a notion of the cumulative second moment for the losses incurred by the algorithm. Moreover, we develop an algorithm based on FTRL with Shannon entropy regularizer that does not require the knowledge of the inverse of the covariance matrix, and achieves a polylogarithmic regret in the stochastic regime while obtaining $\widetilde{O}\big(dK\sqrt{T}\big)$ regret bounds in the adversarial regime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15433 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Best-of-Both-Worlds Algorithms for Linear Contextual Bandits Kuroki, Yuko Rumi, Alberto Tsuchiya, Taira Vitale, Fabio Cesa-Bianchi, Nicolò Machine Learning We study best-of-both-worlds algorithms for $K$-armed linear contextual bandits. Our algorithms deliver near-optimal regret bounds in both the adversarial and stochastic regimes, without prior knowledge about the environment. In the stochastic regime, we achieve the polylogarithmic rate $\frac{(dK)^2\mathrm{poly}\log(dKT)}{Δ_{\min}}$, where $Δ_{\min}$ is the minimum suboptimality gap over the $d$-dimensional context space. In the adversarial regime, we obtain either the first-order $\widetilde{O}(dK\sqrt{L^*})$ bound, or the second-order $\widetilde{O}(dK\sqrt{Λ^*})$ bound, where $L^*$ is the cumulative loss of the best action and $Λ^*$ is a notion of the cumulative second moment for the losses incurred by the algorithm. Moreover, we develop an algorithm based on FTRL with Shannon entropy regularizer that does not require the knowledge of the inverse of the covariance matrix, and achieves a polylogarithmic regret in the stochastic regime while obtaining $\widetilde{O}\big(dK\sqrt{T}\big)$ regret bounds in the adversarial regime. |
| title | Best-of-Both-Worlds Algorithms for Linear Contextual Bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2312.15433 |