中文
相关论文

相关论文: Best Arm Identification for Cascading Bandits in t…

200 篇论文

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)…

We give a complete characterization of the sampling complexity of best Markovian arm identification in one-parameter Markovian bandit models. We derive instance specific nonasymptotic and asymptotic lower bounds which generalize those of…

统计理论 · 数学 2020-07-29 Vrettos Moulos

We consider a stochastic bandit problem with a possibly infinite number of arms. We write $p^*$ for the proportion of optimal arms and $\Delta$ for the minimal mean-gap between optimal and sub-optimal arms. We characterize the optimal…

机器学习 · 计算机科学 2021-11-08 Rianne de Heide , James Cheshire , Pierre Ménard , Alexandra Carpentier

We consider the problem of identifying the best arm in a multi-armed bandit model. Despite a wealth of literature in the traditional fixed budget and fixed confidence regimes of the best arm identification problem, it still remains a…

机器学习 · 统计学 2025-12-08 Michael O. Harding , Kirthevasan Kandasamy

We study the problem of best-arm identification (BAI) in the fixed-budget setting with heterogeneous reward variances. We propose two variance-adaptive BAI algorithms for this setting: SHVar for known reward variances and SHAdaVar for…

机器学习 · 计算机科学 2023-06-14 Anusha Lalitha , Kousha Kalantari , Yifei Ma , Anoop Deoras , Branislav Kveton

We study a stochastic multi-armed bandit setting where arms are partitioned into known clusters, such that the mean rewards of arms within a cluster differ by at most a known threshold. While the clustering structure is known a priori, the…

机器学习 · 计算机科学 2025-08-20 Aakash Gore , Prasanna Chaporkar

We consider a sequential decision-making problem where an agent can take one action at a time and each action has a stochastic temporal extent, i.e., a new action cannot be taken until the previous one is finished. Upon completion, the…

机器学习 · 计算机科学 2020-03-26 P Sharoff , Nishant A. Mehta , Ravi Ganti

Motivated by the need to efficiently identify multiple candidates in high trial-and-error cost tasks such as drug discovery, we propose a near-optimal algorithm to identify all {\epsilon}-best arms (i.e., those at most {\epsilon} worse than…

机器学习 · 统计学 2025-10-02 Zhekai Li , Tianyi Ma , Cheng Hua , Ruihao Zhu

This paper focuses on best-arm identification in multi-armed bandits with bounded rewards. We develop an algorithm that is a fusion of lil-UCB and KL-LUCB, offering the best qualities of the two algorithms in one method. This is achieved by…

统计理论 · 数学 2017-09-13 Bob Mankoff , Robert Nowak , Ervin Tanczos

This paper studies a multi-armed bandit (MAB) version of the range-searching problem. In its basic form, range searching considers as input a set of points (on the real line) and a collection of (real) intervals. Here, with each specified…

机器学习 · 计算机科学 2021-05-05 Siddharth Barman , Ramakrishnan Krishnamurthy , Saladi Rahul

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…

机器学习 · 统计学 2022-03-30 P. N. Karthik , Kota Srinivas Reddy , 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

Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world decision-making pipelines, it is increasingly important that…

机器学习 · 计算机科学 2022-06-23 Romain Camilleri , Andrew Wagenmaker , Jamie Morgenstern , Lalit Jain , Kevin Jamieson

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

This study investigates the experimental design problem for identifying the arm with the highest expected outcome, referred to as best arm identification (BAI). In our experiments, the number of treatment-allocation rounds is fixed. During…

统计理论 · 数学 2024-03-12 Masahiro Kato

A search engine usually outputs a list of $K$ web pages. The user examines this list, from the first web page to the last, and chooses the first attractive page. This model of user behavior is known as the cascade model. In this paper, we…

机器学习 · 计算机科学 2015-05-19 Branislav Kveton , Csaba Szepesvari , Zheng Wen , Azin Ashkan

This paper studies a new variant of the stochastic multi-armed bandits problem where auxiliary information about the arm rewards is available in the form of control variates. In many applications like queuing and wireless networks, the arm…

机器学习 · 计算机科学 2022-01-19 Arun Verma , Manjesh K. Hanawal

We investigate the problem of batched best arm identification in multi-armed bandits, where we aim to identify the best arm from a set of $n$ arms while minimizing both the number of samples and batches. We introduce an algorithm that…

机器学习 · 计算机科学 2025-01-30 Tianyuan Jin , Qin Zhang , Dongruo Zhou

Motivated by modern applications, such as online advertisement and recommender systems, we study the top-$k$ extreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select $k$ arms…

Stochastic multi-armed bandits are a sequential-decision-making framework, where, at each interaction step, the learner selects an arm and observes a stochastic reward. Within the context of best-arm identification (BAI) problems, the goal…

机器学习 · 计算机科学 2024-01-15 Riccardo Poiani , Alberto Maria Metelli , Marcello Restelli