中文
相关论文

相关论文: Worst-Case Regret Bounds for Combinatorial Thompso…

200 篇论文

This paper presents a new dynamic approach to experiment design in settings where, due to interference or other concerns, experimental units are coarse. `Region-split' experiments on online platforms are one example of such a setting. The…

机器学习 · 统计学 2022-02-16 Vivek Farias , Ciamac Moallemi , Tianyi Peng , Andrew Zheng

In this paper we propose a novel experimental design-based algorithm to minimize regret in online stochastic linear and combinatorial bandits. While existing literature tends to focus on optimism-based algorithms--which have been shown to…

机器学习 · 计算机科学 2021-03-02 Andrew Wagenmaker , Julian Katz-Samuels , Kevin Jamieson

This paper studies the stochastic linear bandit problem, where a decision-maker chooses actions from possibly time-dependent sets of vectors in $\mathbb{R}^d$ and receives noisy rewards. The objective is to minimize regret, the difference…

机器学习 · 计算机科学 2023-04-24 Nima Hamidi , Mohsen Bayati

We study a sequential decision problem where the learner faces a sequence of $K$-armed bandit tasks. The task boundaries might be known (the bandit meta-learning setting), or unknown (the non-stationary bandit setting). For a given integer…

We address the problem of regret minimization in logistic contextual bandits, where a learner decides among sequential actions or arms given their respective contexts to maximize binary rewards. Using a fast inference procedure with…

机器学习 · 统计学 2018-05-22 Bianca Dumitrascu , Karen Feng , Barbara E Engelhardt

We study the multi-objective linear contextual bandit problem, where multiple possible conflicting objectives must be optimized simultaneously. We propose \texttt{MOL-TS}, the \textit{first} Thompson Sampling algorithm with Pareto regret…

机器学习 · 统计学 2025-12-02 Somangchan Park , Heesang Ann , Min-hwan Oh

The Competing Bandits framework is a recently emerging area that integrates multi-armed bandits in online learning with stable matching in game theory. While conventional models assume that all players and arms are constantly available, in…

机器学习 · 计算机科学 2026-03-23 Shinnosuke Uba , Yutaro Yamaguchi

We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions.…

机器学习 · 计算机科学 2015-06-11 Gergely Neu

In this paper, we study sequential decision-making for maximizing the Sharpe ratio (SR) in a stochastic multi-armed bandit (MAB) setting. Unlike standard bandit formulations that maximize cumulative reward, SR optimization requires…

机器学习 · 计算机科学 2026-04-02 Mohammad Taha Shah , Sabrina Khurshid , Gourab Ghatak

We consider a combinatorial multi-armed bandit problem for maximum value reward function under maximum value and index feedback. This is a new feedback structure that lies in between commonly studied semi-bandit and full-bandit feedback…

机器学习 · 计算机科学 2023-05-26 Yiliu Wang , Wei Chen , Milan Vojnović

We consider the combinatorial volatile Gaussian process (GP) semi-bandit problem. Each round, an agent is provided a set of available base arms and must select a subset of them to maximize the long-term cumulative reward. We study the…

机器学习 · 计算机科学 2025-02-13 Jack Sandberg , Niklas Åkerblom , Morteza Haghir Chehreghani

Cascading bandit (CB) is a popular model for web search and online advertising, where an agent aims to learn the $K$ most attractive items out of a ground set of size $L$ during the interaction with a user. However, the stationary CB model…

机器学习 · 计算机科学 2020-02-18 Lingda Wang , Huozhi Zhou , Bingcong Li , Lav R. Varshney , Zhizhen Zhao

In this paper, we study the combinatorial semi-bandits (CMAB) and focus on reducing the dependency of the batch-size $K$ in the regret bound, where $K$ is the total number of arms that can be pulled or triggered in each round. First, for…

机器学习 · 计算机科学 2024-11-19 Xutong Liu , Jinhang Zuo , Siwei Wang , Carlee Joe-Wong , John C. S. Lui , Wei Chen

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 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

The multi-armed bandit problem is a popular model for studying exploration/exploitation trade-off in sequential decision problems. Many algorithms are now available for this well-studied problem. One of the earliest algorithms, given by W.…

机器学习 · 计算机科学 2012-04-10 Shipra Agrawal , Navin Goyal

We consider a continuous-time multi-arm bandit problem (CTMAB), where the learner can sample arms any number of times in a given interval and obtain a random reward from each sample, however, increasing the frequency of sampling incurs an…

机器学习 · 计算机科学 2023-04-20 Rahul Vaze , Manjesh K. Hanawal

We revisit the study of optimal regret rates in bandit combinatorial optimization---a fundamental framework for sequential decision making under uncertainty that abstracts numerous combinatorial prediction problems. We prove that the…

机器学习 · 计算机科学 2017-02-27 Alon Cohen , Tamir Hazan , Tomer Koren

We consider a linear stochastic bandit problem involving $M$ agents that can collaborate via a central server to minimize regret. A fraction $\alpha$ of these agents are adversarial and can act arbitrarily, leading to the following tension:…

机器学习 · 计算机科学 2022-06-08 Aritra Mitra , Arman Adibi , George J. Pappas , Hamed Hassani

We study the problem of regret minimization in a multi-armed bandit setup where the agent is allowed to play multiple arms at each round by spreading the resources usually allocated to only one arm. At each iteration the agent selects a…

机器学习 · 计算机科学 2021-06-01 Matias I. Müller , Cristian R. Rojas