中文
相关论文

相关论文: On the Existence of a Complexity in Fixed Budget B…

200 篇论文

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…

统计理论 · 数学 2022-03-08 Antoine Barrier , Aurélien Garivier , Tomáš Kocák

Bandit optimization usually refers to the class of online optimization problems with limited feedback, namely, a decision maker uses only the objective value at the current point to make a new decision and does not have access to the…

机器学习 · 计算机科学 2026-02-18 Yuriy Dorn , Aleksandr Katrutsa , Ilgam Latypov , Anastasiia Soboleva

We study the batched best arm identification (BBAI) problem, where the learner's goal is to identify the best arm while switching the policy as less as possible. In particular, we aim to find the best arm with probability $1-\delta$ for…

机器学习 · 计算机科学 2025-03-05 Tianyuan Jin , Yu Yang , Jing Tang , Xiaokui Xiao , Pan Xu

We study the combinatorial pure exploration problem Best-Set in stochastic multi-armed bandits. In a Best-Set instance, we are given $n$ arms with unknown reward distributions, as well as a family $\mathcal{F}$ of feasible subsets over the…

机器学习 · 计算机科学 2017-06-06 Lijie Chen , Anupam Gupta , Jian Li , Mingda Qiao , Ruosong Wang

The knowledge gradient (KG) algorithm is a popular and effective algorithm for the best arm identification (BAI) problem. Due to the complex calculation of KG, theoretical analysis of this algorithm is difficult, and existing results are…

机器学习 · 统计学 2022-11-23 Yanwen Li , Siyang Gao

A/B testing refers to the task of determining the best option among two alternatives that yield random outcomes. We provide distribution-dependent lower bounds for the performance of A/B testing that improve over the results currently…

统计理论 · 数学 2015-02-25 Emilie Kaufmann , Olivier Cappé , Aurélien Garivier

We study the Bandit Clustering (BC) problem under the fixed confidence setting, where the objective is to group a collection of data sequences (arms) into clusters through sequential sampling from adaptively selected arms at each time step…

机器学习 · 计算机科学 2026-01-15 G Dhinesh Chandran , Kota Srinivas Reddy , Srikrishna Bhashyam

We consider the problem of identifying any $k$ out of the best $m$ arms in an $n$-armed stochastic multi-armed bandit. Framed in the PAC setting, this particular problem generalises both the problem of `best subset selection' and that of…

机器学习 · 计算机科学 2019-01-25 Arghya Roy Chaudhuri , Shivaram Kalyanakrishnan

Motivated by recursive learning in Markov Decision Processes, this paper studies best-arm identification in bandit problems where each arm's reward is drawn from a multinomial distribution with a known support. We compare the performance {…

机器学习 · 计算机科学 2025-02-19 Mehrasa Ahmadipour , élise Crepon , Aurélien Garivier

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…

机器学习 · 计算机科学 2024-08-29 Woojin Jeong , Seungki Min

Mode estimation is a classical problem in statistics with a wide range of applications in machine learning. Despite this, there is little understanding in its robustness properties under possibly adversarial data contamination. In this…

机器学习 · 计算机科学 2020-03-09 Aldo Pacchiano , Heinrich Jiang , Michael I. Jordan

Motivated by real-world applications that necessitate responsible experimentation, we introduce the problem of best arm identification (BAI) with minimal regret. This innovative variant of the multi-armed bandit problem elegantly…

机器学习 · 计算机科学 2024-09-30 Junwen Yang , Vincent Y. F. Tan , Tianyuan Jin

Motivated by a natural problem in online model selection with bandit information, we introduce and analyze a best arm identification problem in the rested bandit setting, wherein arm expected losses decrease with the number of times the arm…

机器学习 · 统计学 2020-12-08 Leonardo Cella , Claudio Gentile , Massimiliano Pontil

We consider the problem of hypothesis testing for discrete distributions. In the standard model, where we have sample access to an underlying distribution $p$, extensive research has established optimal bounds for uniformity testing,…

机器学习 · 计算机科学 2024-12-03 Maryam Aliakbarpour , Piotr Indyk , Ronitt Rubinfeld , Sandeep Silwal

We study finite-armed stochastic bandits where the rewards of each arm might be correlated to those of other arms. We introduce a novel phased algorithm that exploits the given structure to build confidence sets over the parameters of the…

机器学习 · 计算机科学 2020-05-26 Andrea Tirinzoni , Alessandro Lazaric , Marcello Restelli

Top-$2$ methods have become popular in solving the best arm identification (BAI) problem. The best arm, or the arm with the largest mean amongst finitely many, is identified through an algorithm that at any sequential step independently…

机器学习 · 计算机科学 2024-12-17 Agniv Bandyopadhyay , Sandeep Juneja , Shubhada Agrawal

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…

人工智能 · 计算机科学 2021-06-22 Dorian Baudry , Yoan Russac , Olivier Cappé

Motivated by drug design, we consider the best-arm identification problem in generalized linear bandits. More specifically, we assume each arm has a vector of covariates, there is an unknown vector of parameters that is common across the…

机器学习 · 计算机科学 2019-05-21 Abbas Kazerouni , Lawrence M. Wein

We consider a best arm identification (BAI) problem for stochastic bandits with adversarial corruptions in the fixed-budget setting of T steps. We design a novel randomized algorithm, Probabilistic Sequential Shrinking($u$) (PSS($u$)),…

机器学习 · 计算机科学 2021-06-21 Zixin Zhong , Wang Chi Cheung , Vincent Y. F. Tan

We present an efficient and generalised procedure to accurately identify the best (or near best) performing algorithm for each sub-task in a multi-problem domain. Our approach treats this as a set of best arm identification problems for…

机器学习 · 计算机科学 2026-04-22 Matthew Stephenson , Alex Newcombe , Eric Piette , Dennis Soemers