English
Related papers

Related papers: Thompson Sampling for 1-Dimensional Exponential Fa…

200 papers

Most bandit algorithms assume that the reward variances or their upper bounds are known, and that they are the same for all arms. This naturally leads to suboptimal performance and higher regret due to variance overestimation. On the other…

Machine Learning · Computer Science 2023-10-13 Aadirupa Saha , Branislav Kveton

Thompson Sampling is a principled method for balancing exploration and exploitation, but its real-world adoption faces computational challenges in large-scale or non-conjugate settings. While ensemble-based approaches offer partial…

Machine Learning · Computer Science 2025-10-29 Yingru Li , Jiawei Xu , Baoxiang Wang , Zhi-Quan Luo

Gaussian process (GP) bandits provide a powerful framework for performing blackbox optimization of unknown functions. The characteristics of the unknown function depend heavily on the assumed GP prior. Most work in the literature assume…

Machine Learning · Computer Science 2026-03-13 Jack Sandberg , Morteza Haghir Chehreghani

The best arm identification problem requires identifying the best alternative (i.e., arm) in active experimentation using the smallest number of experiments (i.e., arm pulls), which is crucial for cost-efficient and timely decision-making…

Machine Learning · Computer Science 2025-06-17 Kapilan Balagopalan , Tuan Ngo Nguyen , Yao Zhao , Kwang-Sung Jun

Thompson sampling (TS) is a class of algorithms for sequential decision-making, which requires maintaining a posterior distribution over a model. However, calculating exact posterior distributions is intractable for all but the simplest…

Machine Learning · Statistics 2019-02-21 Ruiyi Zhang , Zheng Wen , Changyou Chen , Lawrence Carin

The improving multi-armed bandits problem is a formal model for allocating effort under uncertainty, motivated by scenarios such as investing research effort into new technologies, performing clinical trials, and hyperparameter selection…

Machine Learning · Computer Science 2026-05-22 Avrim Blum , Marten Garicano , Kavya Ravichandran , Dravyansh Sharma

We here adopt Bayesian nonparametric mixture models to extend multi-armed bandits in general, and Thompson sampling in particular, to scenarios where there is reward model uncertainty. In the stochastic multi-armed bandit, the reward for…

Machine Learning · Statistics 2022-08-26 Iñigo Urteaga , Chris H. Wiggins

Multi-task learning in contextual bandits has attracted significant research interest due to its potential to enhance decision-making across multiple related tasks by leveraging shared structures and task-specific heterogeneity. In this…

Machine Learning · Computer Science 2025-11-07 Xia Jiang , Rong J. B. Zhu

In this paper, we propose a Double Thompson Sampling (D-TS) algorithm for dueling bandit problems. As indicated by its name, D-TS selects both the first and the second candidates according to Thompson Sampling. Specifically, D-TS maintains…

Machine Learning · Computer Science 2016-10-28 Huasen Wu , Xin Liu

A challenging aspect of the bandit problem is that a stochastic reward is observed only for the chosen arm and the rewards of other arms remain missing. The dependence of the arm choice on the past context and reward pairs compounds the…

Machine Learning · Statistics 2023-05-02 Wonyoung Kim , Gi-soo Kim , Myunghee Cho Paik

Posterior sampling in contextual bandits with a Gaussian prior can be implemented exactly or approximately using the Laplace approximation. The Gaussian prior is computationally efficient but it cannot describe complex distributions. In…

Machine Learning · Computer Science 2026-02-17 Branislav Kveton , Boris Oreshkin , Youngsuk Park , Aniket Deshmukh , Rui Song

We derive an alternative proof for the regret of Thompson sampling (\ts) in the stochastic linear bandit setting. While we obtain a regret bound of order $\widetilde{O}(d^{3/2}\sqrt{T})$ as in previous results, the proof sheds new light on…

Machine Learning · Statistics 2019-11-06 Marc Abeille , Alessandro Lazaric

We propose a novel framework for structured bandits, which we call an influence diagram bandit. Our framework captures complex statistical dependencies between actions, latent variables, and observations; and thus unifies and extends many…

Machine Learning · Computer Science 2020-07-10 Tong Yu , Branislav Kveton , Zheng Wen , Ruiyi Zhang , Ole J. Mengshoel

For the stochastic multi-armed bandit (MAB) problem from a constrained model that generalizes the classical one, we show that an asymptotic optimality is achievable by a simple strategy extended from the $\epsilon_t$-greedy strategy. We…

Optimization and Control · Mathematics 2018-05-04 Hyeong Soo Chang

Traditional multi-armed bandit (MAB) formulations usually make certain assumptions about the underlying arms' distributions, such as bounds on the support or their tail behaviour. Moreover, such parametric information is usually 'baked'…

Machine Learning · Computer Science 2022-03-29 Anmol Kagrecha , Jayakrishnan Nair , Krishna Jagannathan

This paper studies regret minimization in a multi-armed bandit. It is well known that side information, such as the prior distribution of arm means in Thompson sampling, can improve the statistical efficiency of the bandit algorithm. While…

Machine Learning · Computer Science 2022-03-08 Rong Zhu , Branislav Kveton

Recent advances in contextual bandit optimization and reinforcement learning have garnered interest in applying these methods to real-world sequential decision making problems. Real-world applications frequently have constraints with…

Machine Learning · Computer Science 2019-11-05 Samuel Daulton , Shaun Singh , Vashist Avadhanula , Drew Dimmery , Eytan Bakshy

This technical note presents a new approach to carrying out the kind of exploration achieved by Thompson sampling, but without explicitly maintaining or sampling from posterior distributions. The approach is based on a bootstrap technique…

Machine Learning · Statistics 2015-07-02 Ian Osband , Benjamin Van Roy

In this paper we propose the first multi-armed bandit algorithm based on re-sampling that achieves asymptotically optimal regret simultaneously for different families of arms (namely Bernoulli, Gaussian and Poisson distributions). Unlike…

Machine Learning · Statistics 2020-10-28 Dorian Baudry , Emilie Kaufmann , Odalric-Ambrym Maillard

We consider parametric exponential families of dimension $K$ on the real line. We study a variant of \textit{boundary crossing probabilities} coming from the multi-armed bandit literature, in the case when the real-valued distributions form…

Machine Learning · Statistics 2017-05-25 Odalric-Ambrym Maillard