中文
相关论文

相关论文: Simultaneously Achieving Group Exposure Fairness a…

200 篇论文

We consider the problem of online fair division of indivisible goods to players when there are a finite number of types of goods and player values are drawn from distributions with unknown means. Our goal is to maximize social welfare…

计算机科学与博弈论 · 计算机科学 2024-12-10 Ariel D. Procaccia , Benjamin Schiffer , Shirley Zhang

The paper proposes a novel upper confidence bound (UCB) procedure for identifying the arm with the largest mean in a multi-armed bandit game in the fixed confidence setting using a small number of total samples. The procedure cannot be…

机器学习 · 统计学 2013-12-30 Kevin Jamieson , Matthew Malloy , Robert Nowak , Sébastien Bubeck

Several optimism-based stochastic bandit algorithms -- including UCB, UCB-V, linear UCB, and finite-arm GP-UCB -- achieve logarithmic regret using proofs that, despite superficial differences, follow essentially the same structure. This…

机器学习 · 计算机科学 2025-12-23 Vikram Krishnamurthy

We present conservative distributed multi-task learning in stochastic linear contextual bandits with heterogeneous agents. This extends conservative linear bandits to a distributed setting where M agents tackle different but related tasks…

机器学习 · 计算机科学 2025-04-29 Jiabin Lin , Shana Moothedath

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 investigate a Bayesian $k$-armed bandit problem in the \emph{many-armed} regime, where $k \geq \sqrt{T}$ and $T$ represents the time horizon. Initially, and aligned with recent literature on many-armed bandit problems, we observe that…

机器学习 · 计算机科学 2024-03-21 Mohsen Bayati , Nima Hamidi , Ramesh Johari , Khashayar Khosravi

Upper Confidence Bound (UCB) is arguably the most commonly used method for linear multi-arm bandit problems. While conceptually and computationally simple, this method highly relies on the confidence bounds, failing to strike the optimal…

机器学习 · 计算机科学 2020-06-05 Kaige Yang , Laura Toni

This paper investigates stochastic and adversarial combinatorial multi-armed bandit problems. In the stochastic setting under semi-bandit feedback, we derive a problem-specific regret lower bound, and discuss its scaling with the dimension…

机器学习 · 计算机科学 2015-11-09 Richard Combes , M. Sadegh Talebi , Alexandre Proutiere , Marc Lelarge

We propose $\tt RandUCB$, a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampling (TS), it uses randomization to trade off exploration and…

机器学习 · 计算机科学 2020-03-24 Sharan Vaswani , Abbas Mehrabian , Audrey Durand , Branislav Kveton

We address multi-armed bandits (MAB) where the objective is to maximize the cumulative reward under a probabilistic linear constraint. For a few real-world instances of this problem, constrained extensions of the well-known Thompson…

机器学习 · 计算机科学 2020-05-14 Vidit Saxena , Joseph E. Gonzalez , Joakim Jaldén

Dueling bandits is a prominent framework for decision-making involving preferential feedback, a valuable feature that fits various applications involving human interaction, such as ranking, information retrieval, and recommendation systems.…

机器学习 · 计算机科学 2024-10-16 Qiwei Di , Tao Jin , Yue Wu , Heyang Zhao , Farzad Farnoud , Quanquan Gu

We study fairness in linear bandit problems. Starting from the notion of meritocratic fairness introduced in Joseph et al. [2016], we carry out a more refined analysis of a more general problem, achieving better performance guarantees with…

机器学习 · 计算机科学 2017-06-30 Matthew Joseph , Michael Kearns , Jamie Morgenstern , Seth Neel , Aaron Roth

Due to the broad range of applications of stochastic multi-armed bandit model, understanding the effects of adversarial attacks and designing bandit algorithms robust to attacks are essential for the safe applications of this model. In this…

机器学习 · 计算机科学 2020-10-28 Guanlin Liu , Lifeng lai

Modern systems, such as digital platforms and service systems, increasingly rely on contextual bandits for online decision-making; however, their deployment can inadvertently create unfair exposure among arms, undermining long-term platform…

机器学习 · 统计学 2026-02-05 Qingwen Zhang , Wenjia Wang

We study a novel variant of the multi-armed bandit problem, where at each time step, the player observes an independently sampled context that determines the arms' mean rewards. However, playing an arm blocks it (across all contexts) for a…

机器学习 · 计算机科学 2020-06-18 Soumya Basu , Orestis Papadigenopoulos , Constantine Caramanis , Sanjay Shakkottai

We consider a budgeted combinatorial multi-armed bandit setting where, in every round, the algorithm selects a super-arm consisting of one or more arms. The goal is to minimize the total expected regret after all rounds within a limited…

机器学习 · 计算机科学 2022-02-17 Debojit Das , Shweta Jain , Sujit Gujar

The Rising Multi-Armed Bandit (RMAB) framework models environments where expected rewards of arms increase with plays, which models practical scenarios where performance of each option improves with the repeated usage, such as in robotics…

机器学习 · 计算机科学 2026-02-16 Seockbean Song , Chenyu Gan , Youngsik Yoon , Siwei Wang , Wei Chen , Jungseul Ok

We address a generalization of the bandit with knapsacks problem, where a learner aims to maximize rewards while satisfying an arbitrary set of long-term constraints. Our goal is to design best-of-both-worlds algorithms that perform…

机器学习 · 计算机科学 2024-05-28 Martino Bernasconi , Matteo Castiglioni , Andrea Celli , Federico Fusco

We study the multi-fidelity multi-armed bandit (MF-MAB), an extension of the canonical multi-armed bandit (MAB) problem. MF-MAB allows each arm to be pulled with different costs (fidelities) and observation accuracy. We study both the best…

机器学习 · 计算机科学 2023-06-14 Xuchuang Wang , Qingyun Wu , Wei Chen , John C. S. Lui

The combinatorial multi-armed bandit model is designed to maximize cumulative rewards in the presence of uncertainty by activating a subset of arms in each round. This paper is inspired by two critical applications in wireless networks,…

机器学习 · 计算机科学 2025-09-17 Xiaoyi Wu , Bin Li