paper-with-me

홈 › Papers

An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces

2025-02-04 · Amaury Gouverneur, Borja Rodriguez Gálvez, Tobias Oechtering, Mikael Skoglund

This paper studies the Bayesian regret of the Thompson Sampling algorithm for bandit problems, building on the information-theoretic framework introduced by Russo and Van Roy (2015). Specifically, it extends the rate-distortion analysis of Dong and Van Roy (2018), which provides near-optimal bounds for linear bandits. A limitation of these results is the assumption of a finite action space. We address this by extending the analysis to settings with infinite and continuous action spaces. Additionally, we specialize our results to bandit problems with expected rewards that are Lipschitz continuous with respect to the action space, deriving a regret bound that explicitly accounts for the complexity of the action space.

📄 PDF Abstract BibTeX arXiv:2502.02140

Code (0)

등록된 구현이 없습니다.

Tasks

Thompson Sampling

Similar Papers 제목 키워드 기반

Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits

2022-05-27 · Gergely Neu, Julia Olkhovskaya, Matteo Papini, Ludovic Schwartz

We study the Bayesian regret of the renowned Thompson Sampling algorithm in contextual bandits with binary losses and adversarially-selected contexts. We adapt the information-theoretic perspective of \cite{RvR16} to the…

Multi-Armed BanditsThompson Sampling

An Adversarial Analysis of Thompson Sampling for Full-information Online Learning: from Finite to Infinite Action Spaces

2025-02-20 · Alexander Terenin, Jeffrey Negrea

We develop a form Thompson sampling for online learning under full feedback - also known as prediction with expert advice - where the learner's prior is defined over the space of an adversary's future actions, rather tha…

Bayesian OptimizationThompson Sampling

An Information-Theoretic Analysis of Thompson Sampling

2014-03-21 · Daniel Russo, Benjamin Van Roy

We provide an information-theoretic analysis of Thompson sampling that applies across a broad range of online optimization problems in which a decision-maker must learn from partial feedback. This analysis inherits the s…

Thompson Sampling

Thompson Sampling in Non-Episodic Restless Bandits

2019-10-12 · Young Hun Jung, Marc Abeille, Ambuj Tewari

Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributio…

Open-Ended Question AnsweringThompson Sampling

Satisficing in Time-Sensitive Bandit Learning

2018-03-07 · Daniel Russo, Benjamin Van Roy

Much of the recent literature on bandit learning focuses on algorithms that aim to converge on an optimal action. One shortcoming is that this orientation does not account for time sensitivity, which can play a crucial r…

Thompson Sampling