English
Related papers

Related papers: Thompson sampling: Precise arm-pull dynamics and a…

200 papers

It is well known that in stochastic multi-armed bandits (MAB), the sample mean of an arm is typically not an unbiased estimator of its true mean. In this paper, we decouple three different sources of this selection bias: adaptive…

Statistics Theory · Mathematics 2019-10-29 Jaehyeok Shin , Aaditya Ramdas , Alessandro Rinaldo

Sampling from distributions to find the one with the largest mean arises in a broad range of applications, and it can be mathematically modeled as a multi-armed bandit problem in which each distribution is associated with an arm. This paper…

Machine Learning · Statistics 2013-06-18 Kevin Jamieson , Matthew Malloy , Robert Nowak , Sebastien Bubeck

Much of the recent literature on bandit learning focuses on algorithms that aim to converge on an optimal action. One shortcoming is that this orientation does not account for time sensitivity, which can play a crucial role when learning an…

Machine Learning · Computer Science 2020-01-09 Daniel Russo , Benjamin Van Roy

We give a complete characterization of the complexity of best-arm identification in one-parameter bandit problems. We prove a new, tight lower bound on the sample complexity. We propose the `Track-and-Stop' strategy, which we prove to be…

Statistics Theory · Mathematics 2016-06-02 Aurélien Garivier , Emilie Kaufmann

We propose a new strategy for best-arm identification with fixed confidence of Gaussian variables with bounded means and unit variance. This strategy, called Exploration-Biased Sampling, is not only asymptotically optimal: it is to the best…

Statistics Theory · Mathematics 2022-03-08 Antoine Barrier , Aurélien Garivier , Tomáš Kocák

We study the problem of best-arm identification with fixed budget in stochastic multi-armed bandits with Bernoulli rewards. For the problem with two arms, also known as the A/B testing problem, we prove that there is no algorithm that (i)…

Machine Learning · Statistics 2024-06-05 Po-An Wang , Kaito Ariu , Alexandre Proutiere

We consider the problem of best arm identification in the multi-armed bandit model, under fixed confidence. Given a confidence input $\delta$, the goal is to identify the arm with the highest mean reward with a probability of at least 1 --…

Machine Learning · Statistics 2023-12-21 El Mehdi Saad , Gilles Blanchard , Nicolas Verzelen

This work proposes a secure and dynamic VM allocation strategy for multi-tenant distributed systems using the Thompson sampling approach. The method proves more effective and secure compared to epsilon-greedy and upper confidence bound…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-08 Pravin Patil , Geetanjali Kale , Tanmay Karmarkar , Ruturaj Ghatage

We study best-arm identification in stochastic multi-armed bandits under the fixed-confidence setting, focusing on instances with multiple optimal arms. Unlike prior work that addresses the unknown-number-of-optimal-arms case, we consider…

Machine Learning · Computer Science 2026-03-05 Lan V. Truong

Offline-to-online learning aims to improve online decision-making by leveraging offline logged data. A central challenge in this setting is the distribution shift between offline and online environments. While some existing works attempt to…

Machine Learning · Computer Science 2026-05-15 Bochao Li , Yao Fu , Wei Chen , Fang Kong

We study the problem of identifying the best arm in a multi-armed bandit environment when each arm is a time-homogeneous and ergodic discrete-time Markov process on a common, finite state space. The state evolution on each arm is governed…

Machine Learning · Statistics 2022-03-30 P. N. Karthik , Kota Srinivas Reddy , Vincent Y. F. Tan

We investigate properties of Thompson Sampling in the stochastic multi-armed bandit problem with delayed feedback. In a setting with i.i.d delays, we establish to our knowledge the first regret bounds for Thompson Sampling with arbitrary…

Machine Learning · Computer Science 2022-05-24 Han Wu , Stefan Wager

Restless bandit problems assume time-varying reward distributions of the arms, which adds flexibility to the model but makes the analysis more challenging. We study learning algorithms over the unknown reward distributions and prove a…

Machine Learning · Computer Science 2019-10-15 Young Hun Jung , Marc Abeille , Ambuj Tewari

Non-stationary multi-armed bandit (NS-MAB) problems have recently received significant attention. NS-MAB are typically modelled in two scenarios: abruptly changing, where reward distributions remain constant for a certain period and change…

Machine Learning · Computer Science 2023-05-23 Han Qi , Yue Wang , Li Zhu

The combinatorial stochastic semi-bandit problem is an extension of the classical multi-armed bandit problem in which an algorithm pulls more than one arm at each stage and the rewards of all pulled arms are revealed. One difference with…

Machine Learning · Computer Science 2016-12-07 Rémy Degenne , Vianney Perchet

We present a provably optimal differentially private algorithm for the stochastic multi-arm bandit problem, as opposed to the private analogue of the UCB-algorithm [Mishra and Thakurta, 2015; Tossou and Dimitrakakis, 2016] which doesn't…

Machine Learning · Statistics 2019-05-24 Touqir Sajed , Or Sheffet

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

Motivated by an open direction in existing literature, we study the 1-identification problem, a fundamental multi-armed bandit formulation on pure exploration. The goal is to determine whether there exists an arm whose mean reward is at…

Machine Learning · Computer Science 2025-08-21 Zitian Li , Wang Chi Cheung

In fixed-confidence best arm identification (BAI), the objective is to quickly identify the optimal option while controlling the probability of error below a desired threshold. Despite the plethora of BAI algorithms, existing methods…

Machine Learning · Computer Science 2026-01-05 Brian M. Cho , Nathan Kallus

We consider the infinite-horizon average-reward restless bandit problem. We propose a novel \emph{two-set policy} that maintains two dynamic subsets of arms: one subset of arms has a nearly optimal state distribution and takes actions…

Machine Learning · Computer Science 2024-10-18 Yige Hong , Qiaomin Xie , Yudong Chen , Weina Wang