English
Related papers

Related papers: Odds-Ratio Thompson Sampling to Control for Time-V…

200 papers

In this paper, we introduce and analyze a variant of the Thompson sampling (TS) algorithm for contextual bandits. At each round, traditional TS requires samples from the current posterior distribution, which is usually intractable. To…

Machine Learning · Statistics 2024-07-23 Pierre Clavier , Tom Huix , Alain Durmus

Thompson Sampling (TS) is widely used to address the exploration/exploitation tradeoff in contextual bandits, yet recent theory shows that it does not explore aggressively enough in high-dimensional problems. Feel-Good Thompson Sampling…

Machine Learning · Computer Science 2025-10-27 Emile Anand , Sarah Liaw

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…

Machine Learning · Statistics 2025-02-05 Amaury Gouverneur , Borja Rodriguez Gálvez , Tobias Oechtering , Mikael Skoglund

We discuss a multiple-play multi-armed bandit (MAB) problem in which several arms are selected at each round. Recently, Thompson sampling (TS), a randomized algorithm with a Bayesian spirit, has attracted much attention for its empirically…

Machine Learning · Statistics 2019-03-22 Junpei Komiyama , Junya Honda , Hiroshi Nakagawa

In the multiarmed bandit problem a gambler chooses an arm of a slot machine to pull considering a tradeoff between exploration and exploitation. We study the stochastic bandit problem where each arm has a reward distribution supported in a…

Statistics Theory · Mathematics 2013-03-29 Junya Honda , Akimichi Takemura

We consider a Bayesian budgeted multi-armed bandit problem, in which each arm consumes a different amount of resources when selected and there is a budget constraint on the total amount of resources that can be used. Budgeted Thompson…

Machine Learning · Computer Science 2024-08-29 Woojin Jeong , Seungki Min

Originally motivated by default risk management applications, this paper investigates a novel problem, referred to as the profitable bandit problem here. At each step, an agent chooses a subset of the K possible actions. For each action…

Machine Learning · Statistics 2018-05-09 Mastane Achab , Stephan Clémençon , Aurélien Garivier

This work explores the idea of a causal contextual multi-armed bandit approach to automated marketing, where we estimate and optimize the causal (incremental) effects. Focusing on causal effect leads to better return on investment (ROI) by…

Machine Learning · Computer Science 2018-10-05 Neela Sawant , Chitti Babu Namballa , Narayanan Sadagopan , Houssam Nassif

We study the combinatorial sleeping multi-armed semi-bandit problem with long-term fairness constraints~(CSMAB-F). To address the problem, we adopt Thompson Sampling~(TS) to maximize the total rewards and use virtual queue techniques to…

Machine Learning · Computer Science 2020-05-15 Zhiming Huang , Yifan Xu , Bingshan Hu , Qipeng Wang , Jianping Pan

We consider the non-stationary multi-armed bandit (MAB) framework and propose a Kolmogorov-Smirnov (KS) test based Thompson Sampling (TS) algorithm named TS-KS, that actively detects change points and resets the TS parameters once a change…

Machine Learning · Statistics 2021-10-22 Gourab Ghatak , Hardhik Mohanty , Aniq Ur Rahman

Mobile health (mHealth) interventions often aim to improve distal outcomes, such as clinical conditions, by optimizing proximal outcomes through just-in-time adaptive interventions. Contextual bandits provide a suitable framework for…

Machine Learning · Statistics 2024-07-31 Xueqing Liu , Nina Deliu , Tanujit Chakraborty , Lauren Bell , Bibhas Chakraborty

This paper unifies the design and the analysis of risk-averse Thompson sampling algorithms for the multi-armed bandit problem for a class of risk functionals $\rho$ that are continuous and dominant. We prove generalised concentration bounds…

Machine Learning · Computer Science 2022-04-19 Joel Q. L. Chang , Vincent Y. F. Tan

Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring regions of the state-action space that maximize rewards, with optimistic…

Machine Learning · Computer Science 2025-03-12 Jasmine Bayrooti , Carl Henrik Ek , Amanda Prorok

Bandit algorithms are widely used in sequential decision problems to maximize the cumulative reward. One potential application is mobile health, where the goal is to promote the user's health through personalized interventions based on user…

Machine Learning · Statistics 2022-08-23 Gi-Soo Kim , Hyun-Joon Yang , Jane P. Kim

I study adversarial attacks against stochastic bandit algorithms. At each round, the learner chooses an arm, and a stochastic reward is generated. The adversary strategically adds corruption to the reward, and the learner is only able to…

Machine Learning · Computer Science 2024-03-18 Shiliang Zuo

This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box oracles. Some of these…

Machine Learning · Computer Science 2019-11-26 David Cortes

There has been a recent surge of interest in nonparametric bandit algorithms based on subsampling. One drawback however of these approaches is the additional complexity required by random subsampling and the storage of the full history of…

Artificial Intelligence · Computer Science 2021-06-22 Dorian Baudry , Yoan Russac , Olivier Cappé

Random sampling is an essential tool in the processing and transmission of data. It is used to summarize data too large to store or manipulate and meet resource constraints on bandwidth or battery power. Estimators that are applied to the…

Databases · Computer Science 2015-03-19 Edith Cohen , Haim Kaplan

Adaptive experimentation is increasingly used in educational platforms to personalize learning through dynamic content and feedback. However, standard adaptive strategies such as Thompson Sampling often underperform in real-world…

We use the lens of weak signal asymptotics to study a class of sequentially randomized experiments, including those that arise in solving multi-armed bandit problems. In an experiment with $n$ time steps, we let the mean reward gaps between…

Statistics Theory · Mathematics 2023-06-26 Xu Kuang , Stefan Wager