Corralling Stochastic Bandit Algorithms

2020-06-16 · Raman Arora, Teodor V. Marinov, Mehryar Mohri

We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm. We give two general algorithms for this setting, which we show benefit from favorable regret guarantees. We show that the regret of the corralling algorithms is no worse than that of the best algorithm containing the arm with the highest reward, and depends on the gap between the highest reward and other rewards.

📄 PDF Abstract BibTeX arXiv:2006.09255

Code (0)

등록된 구현이 없습니다.

Corralling a Larger Band of Bandits: A Case Study on Switching Regret for Linear Bandits

2022-02-12 · Haipeng Luo, Mengxiao Zhang, Peng Zhao, Zhi-Hua Zhou

We consider the problem of combining and learning over a set of adversarial bandit algorithms with the goal of adaptively tracking the best one on the fly. The CORRAL algorithm of Agarwal et al. (2017) and its variants (…

Corralling a Band of Bandit Algorithms

2016-12-19 · Alekh Agarwal, Haipeng Luo, Behnam Neyshabur, Robert E. Schapire

We study the problem of combining multiple bandit algorithms (that is, online learning algorithms with partial feedback) with the goal of creating a master algorithm that performs almost as well as the best base algorith…

Multi-Armed Bandits

Pareto Optimal Model Selection in Linear Bandits

2021-02-12 · Yinglun Zhu, Robert Nowak

We study model selection in linear bandits, where the learner must adapt to the dimension (denoted by $d_\star$) of the smallest hypothesis class containing the true linear model while balancing exploration and exploitat…

model Model Selection

Observation-Free Attacks on Stochastic Bandits

2021-12-01 · NeurIPS 2021 12 · Yinglun Xu, Bhuvesh Kumar, Jacob D. Abernethy

We study data corruption attacks on stochastic multi arm bandit algorithms. Existing attack methodologies assume that the attacker can observe the multi arm bandit algorithm's realized behavior which is in contrast to th…

Thompson Sampling

Data Poisoning Attacks on Stochastic Bandits

2019-05-16 · Fang Liu, Ness Shroff

Stochastic multi-armed bandits form a class of online learning problems that have important applications in online recommendation systems, adaptive medical treatment, and many others. Even though potential attacks agains…

Data Poisoning Multi-Armed Bandits Recommendation Systems