中文
相关论文

相关论文: Optimal Best Arm Identification in Two-Armed Bandi…

200 篇论文

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)…

机器学习 · 统计学 2024-06-05 Po-An Wang , Kaito Ariu , Alexandre Proutiere

The restless bandit problem is one of the most well-studied generalizations of the celebrated stochastic multi-armed bandit problem in decision theory. In its ultimate generality, the restless bandit problem is known to be PSPACE-Hard to…

数据结构与算法 · 计算机科学 2009-02-03 Sudipto Guha , Kamesh Munagala , Peng Shi

This paper studies active learning in the context of robust statistics. Specifically, we propose a variant of the Best Arm Identification problem for \emph{contaminated bandits}, where each arm pull has probability $\varepsilon$ of…

统计理论 · 数学 2021-11-16 Jason Altschuler , Victor-Emmanuel Brunel , Alan Malek

Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem. Within the multi-armed bandit literature, the cumulative regret objective enjoys algorithms and analyses for both the…

机器学习 · 计算机科学 2015-03-02 Kevin Jamieson , Ameet Talwalkar

In this paper we consider the problem of best-arm identification in multi-armed bandits in the fixed confidence setting, where the goal is to identify, with probability $1-\delta$ for some $\delta>0$, the arm with the highest mean reward in…

机器学习 · 统计学 2021-09-13 Samarth Gupta , Gauri Joshi , Osman Yağan

We study the $K$-armed dueling bandit problem, a variation of the standard stochastic bandit problem where the feedback is limited to relative comparisons of a pair of arms. We introduce a tight asymptotic regret lower bound that is based…

机器学习 · 统计学 2015-06-30 Junpei Komiyama , Junya Honda , Hisashi Kashima , Hiroshi Nakagawa

We introduce a variant of the classical PAC multi-armed bandit problem. There is an ordered set of $n$ arms $A[1],\dots,A[n]$, each with some stochastic reward drawn from some unknown bounded distribution. The goal is to identify the…

机器学习 · 计算机科学 2018-01-11 Albert Cheu , Ravi Sundaram , Jonathan Ullman

This paper studies two variants of the best arm identification (BAI) problem under the streaming model, where we have a stream of $n$ arms with reward distributions supported on $[0,1]$ with unknown means. The arms in the stream are…

机器学习 · 计算机科学 2024-10-24 Tianyuan Jin , Keke Huang , Jing Tang , Xiaokui Xiao

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…

机器学习 · 计算机科学 2021-09-14 Nadav Merlis , Shie Mannor

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

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

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…

机器学习 · 统计学 2016-04-12 Robert Nishihara , David Lopez-Paz , Léon Bottou

We consider a novel stochastic multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. This models situations where reusing an arm too often is undesirable (e.g. making the same…

机器学习 · 计算机科学 2024-07-31 Soumya Basu , Rajat Sen , Sujay Sanghavi , Sanjay Shakkottai

In this paper, we study sequential testing problems with \emph{overlapping} hypotheses. We first focus on the simple problem of assessing if the mean $\mu$ of a Gaussian distribution is smaller or larger than a fixed $\epsilon>0$; if…

统计理论 · 数学 2021-11-19 Aurélien Garivier , Emilie Kaufmann

The classic multi-armed bandit (MAB) problem tackles the challenge of accruing maximum reward while making decisions under uncertainty. However, in applications, often the goal is to minimize cost subject to a constraint on the minimum…

机器学习 · 计算机科学 2026-05-11 Ishank Juneja , Carlee Joe-Wong , Osman Yağan

We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random covariate. The goal is to maximize cumulative expected reward.…

统计理论 · 数学 2010-03-09 Philippe Rigollet , Assaf Zeevi

Multi-armed bandits (MAB) model sequential decision making problems, in which a learner sequentially chooses arms with unknown reward distributions in order to maximize its cumulative reward. Most of the prior work on MAB assumes that the…

机器学习 · 计算机科学 2018-03-22 Onur Atan , Cem Tekin , Mihaela van der Schaar

We study the best-arm identification problem with fixed confidence when contextual (covariate) information is available in stochastic bandits. Although we can use contextual information in each round, we are interested in the marginalized…

机器学习 · 计算机科学 2024-02-27 Masahiro Kato , Kaito Ariu

In this paper, we consider a novel variant of the multi-armed bandit (MAB) problem, MAB with cost subsidy, which models many real-life applications where the learning agent has to pay to select an arm and is concerned about optimizing…

机器学习 · 计算机科学 2021-03-16 Deeksha Sinha , Karthik Abinav Sankararama , Abbas Kazerouni , Vashist Avadhanula

One of the key drivers of complexity in the classical (stochastic) multi-armed bandit (MAB) problem is the difference between mean rewards in the top two arms, also known as the instance gap. The celebrated Upper Confidence Bound (UCB)…

机器学习 · 计算机科学 2021-10-27 Anand Kalvit , Assaf Zeevi
‹ 上一页 1 8 9 10 下一页 ›