中文
相关论文

相关论文: Nearly Tight Bounds for Cross-Learning Contextual …

200 篇论文

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 study the stochastic multi-armed bandit problem with the graph-based feedback structure introduced by Mannor and Shamir. We analyze the performance of the two most prominent stochastic bandit algorithms, Thompson Sampling and Upper…

机器学习 · 计算机科学 2020-02-17 Thodoris Lykouris , Eva Tardos , Drishti Wali

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

机器学习 · 统计学 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

Variance-dependent regret bounds for linear contextual bandits, which improve upon the classical $\tilde{O}(d\sqrt{K})$ regret bound to $\tilde{O}(d\sqrt{\sum_{k=1}^K\sigma_k^2})$, where $d$ is the context dimension, $K$ is the number of…

机器学习 · 计算机科学 2025-03-18 Jiafan He , Quanquan Gu

This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e. those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. $arm$). We study a particular case of the rested…

机器学习 · 统计学 2024-11-28 Marco Fiandri , Alberto Maria Metelli , Francesco Trov`o

Multiplayer bandits have recently been extensively studied because of their application to cognitive radio networks. While the literature mostly considers synchronous players, radio networks (e.g. for IoT) tend to have asynchronous devices.…

机器学习 · 计算机科学 2023-06-01 Hugo Richard , Etienne Boursier , Vianney Perchet

We consider a multi-armed bandit problem where payoffs are a linear function of an observed stochastic contextual variable. In the scenario where there exists a gap between optimal and suboptimal rewards, several algorithms have been…

数据结构与算法 · 计算机科学 2014-07-08 José Bento , Stratis Ioannidis , S. Muthukrishnan , Jinyun Yan

Contextual multi-armed bandit algorithms are widely used in sequential decision tasks such as news article recommendation systems, web page ad placement algorithms, and mobile health. Most of the existing algorithms have regret proportional…

机器学习 · 统计学 2020-02-14 Gi-Soo Kim , Myunghee Cho Paik

We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the…

机器学习 · 计算机科学 2026-05-18 Zijun Chen , Zihan Zhang

In multi-armed bandit problems, the typical goal is to identify the arm with the highest reward. This paper explores a threshold-based bandit problem, aiming to select an arm based on its relation to a prescribed threshold \(\tau \). We…

机器学习 · 计算机科学 2025-09-03 Chanakya Varude , Jay Chaudhary , Siddharth Kaushik , Prasanna Chaporkar

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

机器学习 · 计算机科学 2026-05-08 Harin Lee , Min-hwan Oh

We consider the adversarial linear contextual bandit setting, which allows for the loss functions associated with each of $K$ arms to change over time without restriction. Assuming the $d$-dimensional contexts are drawn from a fixed known…

机器学习 · 计算机科学 2023-05-25 Julia Olkhovskaya , Jack Mayo , Tim van Erven , Gergely Neu , Chen-Yu Wei

Contextual bandits with linear payoffs, which are also known as linear bandits, provide a powerful alternative for solving practical problems of sequential decisions, e.g., online advertisements. In the era of big data, contextual data…

机器学习 · 计算机科学 2019-03-21 Xiaotian Yu

We study the generalized linear contextual bandit problem within the constraints of limited adaptivity. In this paper, we present two algorithms, $\texttt{B-GLinCB}$ and $\texttt{RS-GLinCB}$, that address, respectively, two prevalent…

机器学习 · 计算机科学 2025-10-29 Ayush Sawarni , Nirjhar Das , Siddharth Barman , Gaurav Sinha

This paper explores a new form of the linear bandit problem in which the algorithm receives the usual stochastic rewards as well as stochastic feedback about which features are relevant to the rewards, the latter feedback being the novel…

机器学习 · 计算机科学 2019-03-13 Urvashi Oswal , Aniruddha Bhargava , Robert Nowak

Motivated by practical needs such as large-scale learning, we study the impact of adaptivity constraints to linear contextual bandits, a central problem in online active learning. We consider two popular limited adaptivity models in…

机器学习 · 计算机科学 2021-04-26 Yufei Ruan , Jiaqi Yang , Yuan Zhou

The Greedy algorithm is the simplest heuristic in sequential decision problem that carelessly takes the locally optimal choice at each round, disregarding any advantages of exploring and/or information gathering. Theoretically, it is known…

机器学习 · 计算机科学 2021-01-05 Matthieu Jedor , Jonathan Louëdec , Vianney Perchet

We consider a multiobjective multiarmed bandit problem with lexicographically ordered objectives. In this problem, the goal of the learner is to select arms that are lexicographic optimal as much as possible without knowing the arm reward…

机器学习 · 计算机科学 2019-07-30 Alihan Hüyük , Cem Tekin

We study the linear contextual bandit problem in the presence of adversarial corruption, where the interaction between the player and a possibly infinite decision set is contaminated by an adversary that can corrupt the reward up to a…

机器学习 · 计算机科学 2021-10-26 Heyang Zhao , Dongruo Zhou , Quanquan Gu

In this paper we initiate a study of non parametric contextual bandits under shape constraints on the mean reward function. Specifically, we study a setting where the context is one dimensional, and the mean reward function is isotonic with…

统计理论 · 数学 2021-10-22 Sabyasachi Chatterjee , Subhabrata Sen