English
Related papers

Related papers: Efficient Inference Without Trading-off Regret in …

200 papers

We study the benefits of sparsity in nonparametric contextual bandit problems, in which the set of candidate features is countably or uncountably infinite. Our contribution is two-fold. First, using a novel reduction to sequences of…

Machine Learning · Statistics 2026-01-16 Hamish Flynn , Julia Olkhovskaya , Paul Rognon-Vael

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

We consider the Multi-Armed Bandit (MAB) problem, where an agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret, i.e., the cumulative difference between…

Machine Learning · Computer Science 2021-09-14 Nadav Merlis , Shie Mannor

We study Thompson Sampling-based algorithms for stochastic bandits with bounded rewards. As the existing problem-dependent regret bound for Thompson Sampling with Gaussian priors [Agrawal and Goyal, 2017] is vacuous when $T \le 288 e^{64}$,…

Machine Learning · Computer Science 2024-05-03 Bingshan Hu , Zhiming Huang , Tianyue H. Zhang , Mathias Lécuyer , Nidhi Hegde

Bandit algorithms sequentially accumulate data using adaptive sampling policies, offering flexibility for real-world applications. However, excessive sampling can be costly, motivating the devolopment of early stopping methods and reliable…

Statistics Theory · Mathematics 2025-02-06 Zihan Cui

Contextual multi-armed bandits are classical models in reinforcement learning for sequential decision-making associated with individual information. A widely-used policy for bandits is Thompson Sampling, where samples from a data-driven…

Machine Learning · Statistics 2021-11-30 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Contextual bandits serve as a fundamental model for many sequential decision making tasks. The most popular theoretically justified approaches are based on the optimism principle. While these algorithms can be practical, they are known to…

Machine Learning · Computer Science 2020-03-17 Botao Hao , Tor Lattimore , Csaba Szepesvari

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

Contextual bandits constitute a classical framework for decision-making under uncertainty. In this setting, the goal is to learn the arms of highest reward subject to contextual information, while the unknown reward parameters of each arm…

Machine Learning · Statistics 2024-02-19 Hongju Park , Mohamad Kazem Shirani Faradonbeh

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

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

Algorithms for hyperparameter optimization abound, all of which work well under different and often unverifiable assumptions. Motivated by the general challenge of sequentially choosing which algorithm to use, we study the more specific…

Machine Learning · Statistics 2016-04-12 Robert Nishihara , David Lopez-Paz , Léon Bottou

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 address the problem of online sequential decision making, i.e., balancing the trade-off between exploiting the current knowledge to maximize immediate performance and exploring the new information to gain long-term benefits using the…

Machine Learning · Computer Science 2022-09-20 Kartik Anand Pant , Amod Hegde , K. V. Srinivas

We study the logistic bandit, in which rewards are binary with success probability $\exp(\beta a^\top \theta) / (1 + \exp(\beta a^\top \theta))$ and actions $a$ and coefficients $\theta$ are within the $d$-dimensional unit ball. While prior…

Machine Learning · Statistics 2019-05-14 Shi Dong , Tengyu Ma , Benjamin Van Roy

We propose an adaptive sampling approach for multiple testing which aims to maximize statistical power while ensuring anytime false discovery control. We consider $n$ distributions whose means are partitioned by whether they are below or…

Machine Learning · Statistics 2019-07-18 Kevin Jamieson , Lalit Jain

Multi-armed bandits are widely used for sequential experimentation in clinical trials, recommendation systems, and online platforms. While regret minimization and valid inference from adaptively collected data have each been studied…

Methodology · Statistics 2026-04-28 Yu-Shiou Willy Lin , Dae Woong Ham , Iavor Bojinov

In this paper, we propose a Thompson Sampling algorithm for \emph{unimodal} bandits, where the expected reward is unimodal over the partially ordered arms. To exploit the unimodal structure better, at each step, instead of exploration from…

Machine Learning · Computer Science 2021-06-17 Long Yang , Zhao Li , Zehong Hu , Shasha Ruan , Shijian Li , Gang Pan , Hongyang Chen

We study the problem of finding the optimal dosage in early stage clinical trials through the multi-armed bandit lens. We advocate the use of the Thompson Sampling principle, a flexible algorithm that can accommodate different types of…

Machine Learning · Statistics 2020-04-09 Maryam Aziz , Emilie Kaufmann , Marie-Karelle Riviere

Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. We propose a simple policy,…

Statistics Theory · Mathematics 2016-03-30 Vianney Perchet , Philippe Rigollet , Sylvain Chassang , Erik Snowberg