中文
相关论文

相关论文: The Sampling Complexity of Condorcet Winner Identi…

200 篇论文

In this paper, we study combinatorial pure exploration for dueling bandits (CPE-DB): we have multiple candidates for multiple positions as modeled by a bipartite graph, and in each round we sample a duel of two candidates on one position…

机器学习 · 计算机科学 2020-06-24 Wei Chen , Yihan Du , Longbo Huang , Haoyu Zhao

Learning from human preference data is becoming a useful tool, from fine-tuning large language models to training reinforcement learning agents. However, in most scenarios, the model is trained on the average preference of all human…

机器学习 · 计算机科学 2026-05-05 Maheed H. Ahmed , Mahsa Ghasemi

A Top Two sampling rule for bandit identification is a method which selects the next arm to sample from among two candidate arms, a leader and a challenger. Due to their simplicity and good empirical performance, they have received…

机器学习 · 统计学 2023-11-08 Marc Jourdan , Rémy Degenne

We consider a bandit problem over a graph where the rewards are not directly observed. Instead, the decision maker can compare two nodes and receive (stochastic) information pertaining to the difference in their value. The graph structure…

机器学习 · 计算机科学 2011-09-13 Dotan Di Castro , Claudio Gentile , Shie Mannor

This paper studies the problem of identifying any $k$ distinct arms among the top $\rho$ fraction (e.g., top 5\%) of arms from a finite or infinite set with a probably approximately correct (PAC) tolerance $\epsilon$. We consider two cases:…

机器学习 · 计算机科学 2020-11-20 Wenbo Ren , Jia Liu , Ness Shroff

We consider the Max $K$-Armed Bandit problem, where a learning agent is faced with several stochastic arms, each a source of i.i.d. rewards of unknown distribution. At each time step the agent chooses an arm, and observes the reward of the…

机器学习 · 统计学 2015-12-25 Yahel David , Nahum Shimkin

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…

机器学习 · 计算机科学 2022-11-04 Yifei Wang , Tavor Baharav , Yanjun Han , Jiantao Jiao , David Tse

We introduce and study a new class of stochastic bandit problems, referred to as predictive bandits. In each round, the decision maker first decides whether to gather information about the rewards of particular arms (so that their rewards…

机器学习 · 计算机科学 2020-04-03 Simon Lindståhl , Alexandre Proutiere , Andreas Johnsson

In bandit best-arm identification, an algorithm is tasked with finding the arm with highest mean reward with a specified accuracy as fast as possible. We study multi-fidelity best-arm identification, in which the algorithm can choose to…

机器学习 · 计算机科学 2025-05-27 Riccardo Poiani , Rémy Degenne , Emilie Kaufmann , Alberto Maria Metelli , Marcello Restelli

In a fixed-confidence pure exploration problem in stochastic multi-armed bandits, an algorithm iteratively samples arms and should stop as early as possible and return the correct answer to a query about the arms distributions. We are…

机器学习 · 计算机科学 2025-02-04 Adrienne Tuynman , Rémy Degenne

We study the problem of best arm identification in linearly parameterised multi-armed bandits. Given a set of feature vectors $\mathcal{X}\subset\mathbb{R}^d,$ a confidence parameter $\delta$ and an unknown vector $\theta^*,$ the goal is to…

机器学习 · 计算机科学 2020-06-16 Mohammadi Zaki , Avi Mohan , Aditya Gopalan

We investigate the sample complexity of learning the optimal arm for multi-task bandit problems. Arms consist of two components: one that is shared across tasks (that we call representation) and one that is task-specific (that we call…

机器学习 · 统计学 2022-11-29 Alessio Russo , Alexandre Proutiere

We introduce a new model of stochastic bandits with adversarial corruptions which aims to capture settings where most of the input follows a stochastic pattern but some fraction of it can be adversarially changed to trick the algorithm,…

机器学习 · 计算机科学 2018-03-28 Thodoris Lykouris , Vahab Mirrokni , Renato Paes Leme

In this paper, we address the problem of identifying the Pareto Set under feasibility constraints in a multivariate bandit setting. Specifically, given a $K$-armed bandit with unknown means $\mu_1, \dots, \mu_K \in \mathbb{R}^d$, the goal…

机器学习 · 统计学 2025-06-11 Cyrille Kone , Emilie Kaufmann , Laura Richert

This paper studies the problem of adaptively sampling from K distributions (arms) in order to identify the largest gap between any two adjacent means. We call this the MaxGap-bandit problem. This problem arises naturally in approximate…

机器学习 · 统计学 2019-06-04 Sumeet Katariya , Ardhendu Tripathy , Robert Nowak

We study the best-arm identification problem in linear bandit, where the rewards of the arms depend linearly on an unknown parameter $\theta^*$ and the objective is to return the arm with the largest reward. We characterize the complexity…

机器学习 · 计算机科学 2014-11-05 Marta Soare , Alessandro Lazaric , Rémi Munos

We consider the best-arm identification problem in multi-armed bandits, which focuses purely on exploration. A player is given a fixed budget to explore a finite set of arms, and the rewards of each arm are drawn independently from a fixed,…

机器学习 · 统计学 2017-08-02 Shahin Shahrampour , Mohammad Noshad , Vahid Tarokh

We study the fixed-budget best-arm identification (BAI) problem in non-stationary linear bandits. Concretely, given a fixed time budget $T\in \mathbb{N}$, finite arm set $\mathcal{X} \subset \mathbb{R}^d$, and a potentially adversarial…

机器学习 · 统计学 2026-03-12 Leo Maynard-Zhang , Zhihan Xiong , Kevin Jamieson , Maryam Fazel

In this paper, we study the stochastic linear bandit problem under the additional requirements of differential privacy, robustness and batched observations. In particular, we assume an adversary randomly chooses a constant fraction of the…

机器学习 · 计算机科学 2023-04-25 Vasileios Charisopoulos , Hossein Esfandiari , Vahab Mirrokni

In the Best-$K$ identification problem (Best-$K$-Arm), we are given $N$ stochastic bandit arms with unknown reward distributions. Our goal is to identify the $K$ arms with the largest means with high confidence, by drawing samples from the…

机器学习 · 计算机科学 2017-05-22 Haotian Jiang , Jian Li , Mingda Qiao