中文
相关论文

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

200 篇论文

We introduce the probably approximately correct (PAC) \emph{Battling-Bandit} problem with the Plackett-Luce (PL) subset choice model--an online learning framework where at each trial the learner chooses a subset of $k$ arms from a fixed set…

机器学习 · 计算机科学 2019-03-05 Aadirupa Saha , Aditya Gopalan

We consider the bandit problem of selecting $K$ out of $N$ arms at each time step. The reward can be a non-linear function of the rewards of the selected individual arms. The direct use of a multi-armed bandit algorithm requires choosing…

机器学习 · 计算机科学 2026-02-16 Mridul Agarwal , Vaneet Aggarwal , Christopher J. Quinn , Abhishek Umrawal

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

We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulling each arm. We employ the same regret as the dueling bandit…

机器学习 · 统计学 2018-09-19 Liyuan Xu , Junya Honda , Masashi Sugiyama

The best arm identification problem in the multi-armed bandit setting is an excellent model of many real-world decision-making problems, yet it fails to capture the fact that in the real-world, safety constraints often must be met while…

机器学习 · 计算机科学 2021-11-25 Zhenlin Wang , Andrew Wagenmaker , Kevin Jamieson

In the latent bandit problem, the learner has access to reward distributions and -- for the non-stationary variant -- transition models of the environment. The reward distributions are conditioned on the arm and unknown latent states. The…

机器学习 · 计算机科学 2022-07-11 Alexander Galozy , Slawomir Nowaczyk

We consider the combinatorial bandits problem with semi-bandit feedback under finite sampling budget constraints, in which the learner can carry out its action only for a limited number of times specified by an overall budget. The action is…

机器学习 · 计算机科学 2022-10-17 Jasmin Brandt , Viktor Bengs , Björn Haddenhorst , Eyke Hüllermeier

In multi-objective decision-making with hierarchical preferences, lexicographic bandits provide a natural framework for optimizing multiple objectives in a prioritized order. In this setting, a learner repeatedly selects arms and observes…

机器学习 · 计算机科学 2025-11-11 Bo Xue , Yuanyu Wan , Zhichao Lu , Qingfu Zhang

We consider the best arm identification (BAI) problem in the $K-$armed bandit framework with a modification - the agent is allowed to play a subset of arms at each time slot instead of one arm. Consequently, the agent observes the sample…

机器学习 · 计算机科学 2026-01-30 Siddhartha Parupudi , Gourab Ghatak

This work considers the problem of selective-sampling for best-arm identification. Given a set of potential options $\mathcal{Z}\subset\mathbb{R}^d$, a learner aims to compute with probability greater than $1-\delta$, $\arg\max_{z\in…

机器学习 · 计算机科学 2021-11-03 Romain Camilleri , Zhihan Xiong , Maryam Fazel , Lalit Jain , Kevin Jamieson

We study the $K$-armed dueling bandit problem, a variation of the traditional multi-armed bandit problem in which feedback is obtained in the form of pairwise comparisons. Previous learning algorithms have focused on the $\textit{fully…

机器学习 · 计算机科学 2022-09-27 Arpit Agarwal , Rohan Ghuge , Viswanath Nagarajan

We address the M-best-arm identification problem in multi-armed bandits. A player has a limited budget to explore K arms (M<K), and once pulled, each arm yields a reward drawn (independently) from a fixed, unknown distribution. The goal is…

机器学习 · 统计学 2017-07-11 Shahin Shahrampour , Vahid Tarokh

We consider a multi-armed bandit setting with finitely many arms, in which each arm yields an $M$-dimensional vector reward upon selection. We assume that the reward of each dimension (a.k.a. {\em objective}) is generated independently of…

机器学习 · 计算机科学 2025-01-24 Zhirui Chen , P. N. Karthik , Yeow Meng Chee , Vincent Y. F. Tan

We consider the problem of near-optimal arm identification in the fixed confidence setting of the infinitely armed bandit problem when nothing is known about the arm reservoir distribution. We (1) introduce a PAC-like framework within which…

机器学习 · 统计学 2018-05-22 Maryam Aziz , Jesse Anderton , Emilie Kaufmann , Javed Aslam

We propose a novel combinatorial stochastic-greedy bandit (SGB) algorithm for combinatorial multi-armed bandit problems when no extra information other than the joint reward of the selected set of $n$ arms at each time step $t\in [T]$ is…

机器学习 · 计算机科学 2023-12-14 Fares Fourati , Christopher John Quinn , Mohamed-Slim Alouini , Vaneet Aggarwal

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

Consider the problem of best arm identification with a security constraint. Specifically, assume a setup of stochastic linear bandits with $K$ arms of dimension $d$. In each arm pull, the player receives a reward that is the sum of the dot…

机器学习 · 计算机科学 2025-07-29 Asaf Cohen , Onur Günlü

Consider $2k-1$ voters, each of which has a preference ranking between $n$ given alternatives. An alternative $A$ is called a Condorcet winner, if it wins against every other alternative $B$ in majority voting (meaning that for every other…

理论经济学 · 经济学 2022-03-28 Lisa Sauermann

Online ranker evaluation is one of the key challenges in information retrieval. While the preferences of rankers can be inferred by interleaving methods, the problem of how to effectively choose the ranker pair that generates the…

信息检索 · 计算机科学 2020-08-11 Chang Li , Ilya Markov , Maarten de Rijke , Masrour Zoghi

We consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder. Our first contribution is a reduction of the confounded setting to the dueling bandit model.…

机器学习 · 统计学 2021-06-10 Johannes Kirschner , Andreas Krause