Mixed Materials
Efficient kernelized bandit algorithms via exploration distributions
| Τίτλος: | Efficient kernelized bandit algorithms via exploration distributions |
|---|---|
| Additional Titles: | We consider a kernelized bandit problem with a compact arm set ${X} \subset \mathbb{R}^d $ and a fixed but unknown reward function $f^*$ with a finite norm in some Reproducing Kernel Hilbert Space (RKHS). We propose a class of computationally efficient kernelized bandit algorithms, which we call GP-Generic, based on a novel concept: exploration distributions. This class of algorithms includes Upper Confidence Bound-based approaches as a special case, but also allows for a variety of randomized algorithms. With careful choice of exploration distribution, our proposed generic algorithm realizes a wide range of concrete algorithms that achieve $\tilde{O}(γ_T\sqrt{T})$ regret bounds, where $γ_T$ characterizes the RKHS complexity. This matches known results for UCB- and Thompson Sampling-based algorithms; we also show that in practice, randomization can yield better practical results. |
| Συγγραφείς: | Hu, Bingshan, He, Zheng, Sutherland, Danica J. |
| Στοιχεία εκδότη: | 2025-06-11 |
| Τύπος εγγράφου: | Mixed materials |
| Όροι ευρετηρίου: | Machine Learning, text |
| Σύνδεσμος: | |
| Διαθεσιμότητα: | Open access content. Open access content |
| Other Numbers: | COO oai:arXiv.org:2506.10091 1577583228 |
| Πηγή συνεισφοράς: | CORNELL UNIV From OAIster®, provided by the OCLC Cooperative. |
| Αριθμός Καταχώρησης: | edsoai.on1577583228 |
| Βάση Δεδομένων: | OAIster |
| Η περιγραφή δεν είναι διαθέσιμη |