English
Related papers

Related papers: On the Suboptimality of Thompson Sampling in High …

200 papers

This paper presents a new dynamic approach to experiment design in settings where, due to interference or other concerns, experimental units are coarse. `Region-split' experiments on online platforms are one example of such a setting. The…

Machine Learning · Statistics 2022-02-16 Vivek Farias , Ciamac Moallemi , Tianyi Peng , Andrew Zheng

We study a generalization of the multi-armed bandit problem with multiple plays where there is a cost associated with pulling each arm and the agent has a budget at each time that dictates how much she can expect to spend. We derive an…

Machine Learning · Statistics 2019-09-13 Alexander Luedtke , Emilie Kaufmann , Antoine Chambaz

Contextual bandits are a core technology for personalized mobile health interventions, where decision-making requires adapting to complex, non-linear user behaviors. While Thompson Sampling (TS) is a preferred strategy for these problems,…

Machine Learning · Statistics 2026-02-10 Ruizhe Deng , Bibhas Chakraborty , Ran Chen , Yan Shuo Tan

We study the stochastic linear bandit problem with multiple arms over $T$ rounds, where the covariate dimension $d$ may exceed $T$, but each arm-specific parameter vector is $s$-sparse. We begin by analyzing the sequential estimation…

Statistics Theory · Mathematics 2025-05-26 Jingyu Liu , Yanglei Song

This paper is motivated by recent research in the $d$-dimensional stochastic linear bandit literature, which has revealed an unsettling discrepancy: algorithms like Thompson sampling and Greedy demonstrate promising empirical performance,…

Machine Learning · Computer Science 2025-05-20 Yuwei Luo , Mohsen Bayati

This paper investigates the problem of generalized linear bandits with heavy-tailed rewards, whose $(1+\epsilon)$-th moment is bounded for some $\epsilon\in (0,1]$. Although there exist methods for generalized linear bandits, most of them…

Machine Learning · Computer Science 2023-10-31 Bo Xue , Yimu Wang , Yuanyu Wan , Jinfeng Yi , Lijun Zhang

Thompson sampling (TS) has optimal regret and excellent empirical performance in multi-armed bandit problems. Yet, in Bayesian optimization, TS underperforms popular acquisition functions (e.g., EI, UCB). TS samples arms according to the…

Machine Learning · Statistics 2024-12-02 David Sweet

We study Thompson Sampling algorithms for stochastic multi-armed bandits in the batched setting, in which we want to minimize the regret over a sequence of arm pulls using a small number of policy changes (or, batches). We propose two…

Machine Learning · Computer Science 2021-08-17 Nikolai Karpov , Qin Zhang

Thompson Sampling has recently been shown to be optimal in the Bernoulli Multi-Armed Bandit setting[Kaufmann et al., 2012]. This bandit problem assumes stationary distributions for the rewards. It is often unrealistic to model the real…

Machine Learning · Computer Science 2013-02-18 Joseph Mellor , Jonathan Shapiro

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

We consider the problem of adaptively placing sensors along an interval to detect stochastically-generated events. We present a new formulation of the problem as a continuum-armed bandit problem with feedback in the form of partial…

In algorithm optimization in reinforcement learning, how to deal with the exploration-exploitation dilemma is particularly important. Multi-armed bandit problem can optimize the proposed solutions by changing the reward distribution to…

Machine Learning · Statistics 2022-03-28 Zhendong Shi , Ercan E. Kuruoglu , Xiaoli Wei

We consider the problem of statistical inference when the data is collected via a Thompson Sampling-type algorithm. While Thompson Sampling (TS) is known to be both asymptotically optimal and empirically effective, its adaptive sampling…

Machine Learning · Statistics 2026-03-17 Budhaditya Halder , Shubhayan Pan , Koulik Khamaru

Multi-armed bandit methods have been used for dynamic experiments particularly in online services. Among the methods, thompson sampling is widely used because it is simple but shows desirable performance. Many thompson sampling methods for…

Machine Learning · Computer Science 2020-03-05 Sulgi Kim , Kyungmin Kim

Given a set of arms $\mathcal{Z}\subset \mathbb{R}^d$ and an unknown parameter vector $\theta_\ast\in\mathbb{R}^d$, the pure exploration linear bandit problem aims to return $\arg\max_{z\in \mathcal{Z}} z^{\top}\theta_{\ast}$, with high…

Machine Learning · Statistics 2023-10-26 Zhaoqi Li , Kevin Jamieson , Lalit Jain

This paper considers the distributed bandit convex optimization problem with time-varying constraints. In this problem, the global loss function is the average of all the local convex loss functions, which are unknown beforehand. Each agent…

Systems and Control · Electrical Eng. & Systems 2025-04-25 Kunpeng Zhang , Lei Xu , Xinlei Yi , Guanghui Wen , Lihua Xie , Tianyou Chai , Tao Yang

We advance the study of incentivized bandit exploration, in which arm choices are viewed as recommendations and are required to be Bayesian incentive compatible. Recent work has shown under certain independence assumptions that after…

Computer Science and Game Theory · Computer Science 2024-09-25 Mark Sellke

We introduce a framework for Thompson sampling (TS) contextual bandit algorithms, in which the algorithm's ability to quantify uncertainty and make decisions depends on the quality of a generative model that is learned offline. Instead of…

Machine Learning · Computer Science 2025-11-13 Kelly W. Zhang , Tiffany Tianhui Cai , Hongseok Namkoong , Daniel Russo

We study the linear bandit problem that accounts for partially observable features. Without proper handling, unobserved features can lead to linear regret in the decision horizon $T$, as their influence on rewards is unknown. To tackle this…

Machine Learning · Statistics 2025-08-19 Wonyoung Kim , Sungwoo Park , Garud Iyengar , Assaf Zeevi , Min-hwan Oh

We study the stochastic linear bandits with parameter noise model, in which the reward of action $a$ is $a^\top \theta$ where $\theta$ is sampled i.i.d. We show a regret upper bound of $\widetilde{O} (\sqrt{d T \log (K/\delta)…

Machine Learning · Computer Science 2026-05-26 Daniel Ezer , Alon Peled-Cohen , Yishay Mansour