paper-with-me

Papers

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 each round. We show that the exponential-weight algorithm achieves $\tilde{O}(\sqrt{T γ_T})$ adversarial regret, where $T$ and $γ_T$ denote the number of total rounds and the maximum information gain, respectively. For squared exponential (SE) and $ν$-Matérn kernels, we also show algorithm-independent lower bounds that guarantee the optimality of our algorithm up to polylogarithmic factors. Furthermore, we present a computationally efficient variant of our algorithm using Nyström approximation while maintaining nearly optimal regret guarantees.

📄 PDF Abstract BibTeX arXiv:2605.10299

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

An algorithm with nearly optimal pseudo-regret for both stochastic and adversarial bandits

2016-05-27 · Peter Auer, Chao-Kai Chiang

We present an algorithm that achieves almost optimal pseudo-regret bounds against adversarial and stochastic bandits. Against adversarial bandits the pseudo-regret is $O(K\sqrt{n \log n})$ and against stochastic bandits …

Efficient Kernel UCB for Contextual Bandits

2022-02-11 · Houssam Zenati, Alberto Bietti, Eustache Diemert, Julien Mairal 외

In this paper, we tackle the computational efficiency of kernelized UCB algorithms in contextual bandits. While standard methods require a O(CT^3) complexity where T is the horizon and the constant C is related to optimi…

Computational EfficiencyMulti-Armed Bandits

Better Algorithms for Stochastic Bandits with Adversarial Corruptions

2019-02-22 · Anupam Gupta, Tomer Koren, Kunal Talwar

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our a…

Multi-Armed Bandits

Communication Efficient Distributed Learning for Kernelized Contextual Bandits

2022-06-10 · Chuanhao Li, Huazheng Wang, Mengdi Wang, Hongning Wang

We tackle the communication efficiency challenge of learning kernelized contextual bandits in a distributed setting. Despite the recent advances in communication-efficient distributed bandit learning, existing solutions …

Multi-Armed Bandits

Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications

2023-02-07 · Johannes Kirschner, Tor Lattimore, Andreas Krause

Partial monitoring is an expressive framework for sequential decision-making with an abundance of applications, including graph-structured and dueling bandits, dynamic pricing and transductive feedback models. We survey …

Decision MakingSequential Decision Making