paper-with-me

Papers

Approximation Theory Based Methods for RKHS Bandits

2020-10-23 · Sho Takemori, Masahiro Sato

The RKHS bandit problem (also called kernelized multi-armed bandit problem) is an online optimization problem of non-linear functions with noisy feedback. Although the problem has been extensively studied, there are unsatisfactory results for some problems compared to the well-studied linear bandit case. Specifically, there is no general algorithm for the adversarial RKHS bandit problem. In addition, high computational complexity of existing algorithms hinders practical application. We address these issues by considering a novel amalgamation of approximation theory and the misspecified linear bandit problem. Using an approximation method, we propose efficient algorithms for the stochastic RKHS bandit problem and the first general algorithm for the adversarial RKHS bandit problem. Furthermore, we empirically show that one of our proposed methods has comparable cumulative regret to IGP-UCB and its running time is much shorter.

📄 PDF Abstract BibTeX arXiv:2010.12167

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Nearly-Optimal Algorithm for Adversarial Kernelized Bandits

2026-05-11 · Shogo Iwazaki arxiv

This paper studies kernelized bandits (also known as Gaussian process bandits) in an adversarial environment, where the reward functions in a known reproducing kernel Hilbert space (RKHS) may be adversarially chosen at e…

Generalization Properties of hyper-RKHS and its Applications

2018-09-26 · Fanghui Liu, Lei Shi, Xiaolin Huang, Jie Yang 외

This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence…

Learning Theoryregression

Weighted Gaussian Process Bandits for Non-stationary Environments

2021-07-06 · Yuntian Deng, Xingyu Zhou, Baekjin Kim, Ambuj Tewari 외

In this paper, we consider the Gaussian process (GP) bandit optimization problem in a non-stationary environment. To capture external changes, the black-box function is allowed to be time-varying within a reproducing ker…

regression

Adaptation to Misspecified Kernel Regularity in Kernelised Bandits

2023-04-26 · Yusha Liu, Aarti Singh

In continuum-armed bandit problems where the underlying function resides in a reproducing kernel Hilbert space (RKHS), namely, the kernelised bandit problems, an important open problem remains of how well learning algori…

Model Selection

Finite-Time Analysis of Kernelised Contextual Bandits

2013-09-26 · Michal Valko, Nathaniel Korda, Remi Munos, Ilias Flaounas 외

We tackle the problem of online reward maximisation over a large finite set of actions described by their contexts. We focus on the case when the number of actions is too big to sample all of them even once. However we a…

Multi-Armed Bandits