English
Related papers

Related papers: Local Asymptotic Normality for Multi-Armed Bandits

200 papers

In the infinite-armed bandit problem, each arm's average reward is sampled from an unknown distribution, and each arm can be sampled further to obtain noisy estimates of the average reward of that arm. Prior work focuses on identifying the…

Machine Learning · Computer Science 2022-11-04 Yifei Wang , Tavor Baharav , Yanjun Han , Jiantao Jiao , David Tse

We develop asymptotically optimal policies for the multi armed bandit (MAB), problem, under a cost constraint. This model is applicable in situations where each sample (or activation) from a population (bandit) incurs a known bandit…

Machine Learning · Statistics 2015-12-18 Apostolos N. Burnetas , Odysseas Kanavetas , Michael N. Katehakis

Adaptively collected data has become ubiquitous within modern practice. However, even seemingly benign adaptive sampling schemes can introduce severe biases, rendering traditional statistical inference tools inapplicable. This can be…

Statistics Theory · Mathematics 2025-12-02 Wei Fan , Kevin Tan , Yuting Wei

This paper investigates the problem of best arm identification in $\textit{contaminated}$ stochastic multi-arm bandits. In this setting, the rewards obtained from any arm are replaced by samples from an adversarial model with probability…

Machine Learning · Computer Science 2021-11-16 Arpan Mukherjee , Ali Tajer , Pin-Yu Chen , Payel Das

We consider the best arm identification (BAI) problem in the $K-$armed bandit framework with a modification - the agent is allowed to play a subset of arms at each time slot instead of one arm. Consequently, the agent observes the sample…

Machine Learning · Computer Science 2026-01-30 Siddhartha Parupudi , Gourab Ghatak

We consider a stochastic multi-armed bandit setting where reward must be actively queried for it to be observed. We provide tight lower and upper problem-dependent guarantees on both the regret and the number of queries. Interestingly, we…

Machine Learning · Computer Science 2022-10-28 Nadav Merlis , Yonathan Efroni , Shie Mannor

This paper considers the multi-armed thresholding bandit problem -- identifying all arms whose expected rewards are above a predefined threshold via as few pulls (or rounds) as possible -- proposed by Locatelli et al. [2016] recently.…

Machine Learning · Statistics 2017-07-11 Jie Zhong , Yijun Huang , Ji Liu

De Haan and Pereira (2006) provided models for spatial extremes in the case of stationarity, which depend on just one parameter {\beta} > 0 measuring tail dependence, and they proposed different estimators for this parameter. This framework…

Statistics Theory · Mathematics 2012-02-24 Stefan Aulbach , Michael Falk

Consider a nonparametric contextual multi-arm bandit problem where each arm $a \in [K]$ is associated to a nonparametric reward function $f_a: [0,1] \to \mathbb{R}$ mapping from contexts to the expected reward. Suppose that there is a large…

Machine Learning · Computer Science 2019-08-06 Nirandika Wanigasekara , Christina Lee Yu

We investigate the fixed-budget best-arm identification (BAI) problem for linear bandits in a potentially non-stationary environment. Given a finite arm set $\mathcal{X}\subset\mathbb{R}^d$, a fixed budget $T$, and an unpredictable sequence…

Machine Learning · Computer Science 2024-02-16 Zhihan Xiong , Romain Camilleri , Maryam Fazel , Lalit Jain , Kevin Jamieson

We study the stochastic multi-armed bandit problem with non-equivalent multiple plays where, at each step, an agent chooses not only a set of arms, but also their order, which influences reward distribution. In several problem formulations…

Machine Learning · Computer Science 2015-07-20 Aleksandr Vorobev , Gleb Gusev

A standard assumption adopted in the multi-armed bandit (MAB) framework is that the mean rewards are constant over time. This assumption can be restrictive in the business world as decision-makers often face an evolving environment where…

Machine Learning · Computer Science 2021-08-24 Ningyuan Chen , Chun Wang , Longlin Wang

We consider a generalization of stochastic bandits where the set of arms, $\cX$, is allowed to be a generic measurable space and the mean-payoff function is "locally Lipschitz" with respect to a dissimilarity function that is known to the…

Machine Learning · Computer Science 2011-04-15 Sébastien Bubeck , Rémi Munos , Gilles Stoltz , Csaba Szepesvari

We study the best-arm identification problem in multi-armed bandits with stochastic, potentially private rewards, when the goal is to identify the arm with the highest quantile at a fixed, prescribed level. First, we propose a (non-private)…

Machine Learning · Statistics 2022-12-06 Kontantinos E. Nikolakakis , Dionysios S. Kalogerias , Or Sheffet , Anand D. Sarwate

Thompson sampling (TS) is widely used for stochastic multi-armed bandits, yet its inferential properties under adaptive data collection are subtle. Classical asymptotic theory for sample means can fail because arm-specific sample sizes are…

Machine Learning · Computer Science 2026-02-06 Shunxing Yan , Han Zhong

Recent work has considered natural variations of the multi-armed bandit problem, where the reward distribution of each arm is a special function of the time passed since its last pulling. In this direction, a simple (yet widely applicable)…

Machine Learning · Computer Science 2021-05-25 Alexia Atsidakou , Orestis Papadigenopoulos , Soumya Basu , Constantine Caramanis , Sanjay Shakkottai

We propose the first fully-adaptive algorithm for pure exploration in linear bandits---the task to find the arm with the largest expected reward, which depends on an unknown parameter linearly. While existing methods partially or entirely…

Machine Learning · Statistics 2017-10-17 Liyuan Xu , Junya Honda , Masashi Sugiyama

We consider a multi-armed bandit setting in which each arm has a public and a private reward distribution. An observer expects an agent to follow Thompson Sampling according to the public rewards, however, the deceptive agent aims to…

Machine Learning · Computer Science 2025-10-13 I. Arda Vurankaya , Mustafa O. Karabag , Wesley A. Suttle , Jesse Milzman , David Fridovich-Keil , Ufuk Topcu

In the context of a large system of $N$ neurons interacting through spike events in a mean-field regime as $N\rightarrow \infty$, we characterize the estimation of a multidimensional parameter in the spiking rate, when the neural states are…

Statistics Theory · Mathematics 2026-05-06 Aline Duarte , Dasha Loukianova , Aurélien Velleret

We study fixed-confidence Best Arm Identification (BAI) in semiparametric bandits, where rewards are linear in arm features plus an unknown additive baseline shift. Unlike linear-bandit BAI, this setting requires orthogonalized regression,…

Machine Learning · Statistics 2026-04-07 Seok-Jin Kim