中文
相关论文

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

200 篇论文

In this work we consider adversarial contextual bandits with risk constraints. At each round, nature prepares a context, a cost for each arm, and additionally a risk for each arm. The learner leverages the context to pull an arm and then…

机器学习 · 计算机科学 2016-10-18 Wen Sun , Debadeepta Dey , Ashish Kapoor

We consider the regret minimization task in a dueling bandits problem with context information. In every round of the sequential decision problem, the learner makes a context-dependent selection of two choice alternatives (arms) to be…

机器学习 · 计算机科学 2022-10-14 Viktor Bengs , Aadirupa Saha , Eyke Hüllermeier

A central problem in online learning and decision making -- from bandits to reinforcement learning -- is to understand what modeling assumptions lead to sample-efficient learning guarantees. We consider a general adversarial decision making…

机器学习 · 计算机科学 2022-06-28 Dylan J. Foster , Alexander Rakhlin , Ayush Sekhari , Karthik Sridharan

Top Two algorithms arose as an adaptation of Thompson sampling to best arm identification in multi-armed bandit models (Russo, 2016), for parametric families of arms. They select the next arm to sample from by randomizing among two…

机器学习 · 统计学 2022-10-05 Marc Jourdan , Rémy Degenne , Dorian Baudry , Rianne de Heide , Emilie Kaufmann

We consider a stochastic multi-armed bandit setting where reward must be actively queried for it to be observed. We provide tight lower and upper problem-dependent guarantees on both the regret and the number of queries. Interestingly, we…

机器学习 · 计算机科学 2022-10-28 Nadav Merlis , Yonathan Efroni , Shie Mannor

We study the problem of best-arm identification in a distributed variant of the multi-armed bandit setting, with a central learner and multiple agents. Each agent is associated with an arm of the bandit, generating stochastic rewards…

机器学习 · 计算机科学 2023-05-02 Fathima Zarin Faizal , Adway Girish , Manjesh Kumar Hanawal , Nikhil Karamchandani

We study the non-stationary dueling bandits problem with $K$ arms, where the time horizon $T$ consists of $M$ stationary segments, each of which is associated with its own preference matrix. The learner repeatedly selects a pair of arms and…

机器学习 · 计算机科学 2022-02-03 Patrick Kolpaczki , Viktor Bengs , Eyke Hüllermeier

This paper studies the fixed-confidence best arm identification (BAI) problem in the bandit framework in the canonical single-parameter exponential models. For this problem, many policies have been proposed, but most of them require solving…

机器学习 · 统计学 2025-08-12 Jongyeong Lee , Junya Honda , Masashi Sugiyama

Combinatorial Multi-Armed Bandit with fairness constraints is a framework where multiple arms form a super arm and can be pulled in each round under uncertainty to maximize cumulative rewards while ensuring the minimum average reward…

机器学习 · 计算机科学 2025-01-14 Xiaoyi Wu , Bo Ji , Bin Li

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

We study best-arm identification with fixed confidence in bandit models with graph smoothness constraint. We provide and analyze an efficient gradient ascent algorithm to compute the sample complexity of this problem as a solution of a…

机器学习 · 计算机科学 2020-05-21 Tomáš Kocák , Aurélien Garivier

We adress the problem of dueling bandits defined on partially ordered sets, or posets. In this setting, arms may not be comparable, and there may be several (incomparable) optimal arms. We propose an algorithm, UnchainedBandits, that…

机器学习 · 计算机科学 2016-06-10 Julien Audiffren , Ralaivola Liva

We give a new algorithm for best arm identification in linearly parameterised bandits in the fixed confidence setting. The algorithm generalises the well-known LUCB algorithm of Kalyanakrishnan et al. (2012) by playing an arm which…

机器学习 · 计算机科学 2019-11-11 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan

We propose EB-TC$\varepsilon$, a novel sampling rule for $\varepsilon$-best arm identification in stochastic bandits. It is the first instance of Top Two algorithm analyzed for approximate best arm identification. EB-TC$\varepsilon$ is an…

机器学习 · 统计学 2023-11-07 Marc Jourdan , Rémy Degenne , Emilie Kaufmann

We study fixed-confidence Best Arm Identification (BAI) in semiparametric bandits, where rewards are linear in arm features plus an unknown additive baseline shift. Unlike linear-bandit BAI, this setting requires orthogonalized regression,…

机器学习 · 统计学 2026-04-07 Seok-Jin Kim

We consider PAC-learning a good item from $k$-subsetwise feedback information sampled from a Plackett-Luce probability model, with instance-dependent sample complexity performance. In the setting where subsets of a fixed size can be tested…

机器学习 · 计算机科学 2020-02-28 Aadirupa Saha , Aditya Gopalan

We consider the problem of learning to choose actions using contextual information when provided with limited feedback in the form of relative pairwise comparisons. We study this problem in the dueling-bandits framework of Yue et al.…

机器学习 · 计算机科学 2015-06-16 Miroslav Dudík , Katja Hofmann , Robert E. Schapire , Aleksandrs Slivkins , Masrour Zoghi

We study the corrupted bandit problem, i.e. a stochastic multi-armed bandit problem with $k$ unknown reward distributions, which are heavy-tailed and corrupted by a history-independent adversary or Nature. To be specific, the reward…

机器学习 · 计算机科学 2023-03-22 Debabrota Basu , Odalric-Ambrym Maillard , Timothée Mathieu

We consider the classic problem of $(\epsilon,\delta)$-PAC learning a best arm where the goal is to identify with confidence $1-\delta$ an arm whose mean is an $\epsilon$-approximation to that of the highest mean arm in a multi-armed bandit…

机器学习 · 计算机科学 2020-06-23 Avinatan Hassidim , Ron Kupfer , Yaron Singer

The objective of canonical multi-armed bandits is to identify and repeatedly select an arm with the largest reward, often in the form of the expected value of the arm's probability distribution. Such a utilitarian perspective and focus on…

机器学习 · 统计学 2025-05-01 Meltem Tatlı , Arpan Mukherjee , Prashanth L. A. , Karthikeyan Shanmugam , Ali Tajer