中文
相关论文

相关论文: Thompson Sampling for Combinatorial Semi-bandits w…

200 篇论文

Thompson Sampling has been widely used for contextual bandit problems due to the flexibility of its modeling power. However, a general theory for this class of methods in the frequentist setting is still lacking. In this paper, we present a…

机器学习 · 计算机科学 2021-10-05 Tong Zhang

In combinatorial semi-bandits, a learner repeatedly selects from a combinatorial decision set of arms, receives the realized sum of rewards, and observes the rewards of the individual selected arms as feedback. In this paper, we extend this…

机器学习 · 计算机科学 2025-09-17 Yuxiao Wen

We consider a finite-armed structured bandit problem in which mean rewards of different arms are known functions of a common hidden parameter $\theta^*$. Since we do not place any restrictions of these functions, the problem setting…

机器学习 · 统计学 2021-02-04 Samarth Gupta , Shreyas Chaudhari , Subhojyoti Mukherjee , Gauri Joshi , Osman Yağan

We study the matroid semi-bandits problem, where at each round the learner plays a subset of $K$ arms from a feasible set, and the goal is to maximize the expected cumulative linear rewards. Existing algorithms have per-round time…

机器学习 · 计算机科学 2024-05-29 Ruo-Chun Tzeng , Naoto Ohsaka , Kaito Ariu

Thompson sampling (TS) has optimal regret and excellent empirical performance in multi-armed bandit problems. Yet, in Bayesian optimization, TS underperforms popular acquisition functions (e.g., EI, UCB). TS samples arms according to the…

机器学习 · 统计学 2024-12-02 David Sweet

In many biomedical, science, and engineering problems, one must sequentially decide which action to take next so as to maximize rewards. One general class of algorithms for optimizing interactions with the world, while simultaneously…

机器学习 · 统计学 2021-05-05 Iñigo Urteaga , Chris H. Wiggins

Thompson sampling has impressive empirical performance for many multi-armed bandit problems. But current algorithms for Thompson sampling only work for the case of conjugate priors since these algorithms require to infer the posterior,…

机器学习 · 计算机科学 2017-08-17 Yichi Zhou , Jun Zhu , Jingwei Zhuo

We study the multi-agent multi-armed bandit (MAMAB) problem, where $m$ agents are factored into $\rho$ overlapping groups. Each group represents a hyperedge, forming a hypergraph over the agents. At each round of interaction, the learner…

机器学习 · 计算机科学 2023-12-27 Tianyuan Jin , Hao-Lun Hsu , William Chang , Pan Xu

We investigate the problem of maximizing social welfare while ensuring fairness in a multi-agent multi-armed bandit (MA-MAB) setting. In this problem, a centralized decision-maker takes actions over time, generating random rewards for…

机器学习 · 计算机科学 2025-06-23 Piyushi Manupriya , Himanshu , SakethaNath Jagarlapudi , Ganesh Ghalme

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

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

Thompson sampling for multi-armed bandit problems is known to enjoy favorable performance in both theory and practice. However, it suffers from a significant limitation computationally, arising from the need for samples from posterior…

机器学习 · 计算机科学 2020-06-19 Eric Mazumdar , Aldo Pacchiano , Yi-an Ma , Peter L. Bartlett , Michael I. Jordan

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 stochastic bandit problem with a possibly infinite number of arms. We write $p^*$ for the proportion of optimal arms and $\Delta$ for the minimal mean-gap between optimal and sub-optimal arms. We characterize the optimal…

机器学习 · 计算机科学 2021-11-08 Rianne de Heide , James Cheshire , Pierre Ménard , Alexandra Carpentier

Thompson Sampling has been demonstrated in many complex bandit models, however the theoretical guarantees available for the parametric multi-armed bandit are still limited to the Bernoulli case. Here we extend them by proving asymptotic…

机器学习 · 统计学 2013-07-15 Nathaniel Korda , Emilie Kaufmann , Remi Munos

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 study the Improving Multi-Armed Bandit (IMAB) problem, where the reward obtained from an arm increases with the number of pulls it receives. This model provides an elegant abstraction for many real-world problems in domains such as…

机器学习 · 计算机科学 2022-08-22 Vishakha Patil , Vineet Nair , Ganesh Ghalme , Arindam Khan

We consider stochastic bandit problems with a continuous set of arms and where the expected reward is a continuous and unimodal function of the arm. No further assumption is made regarding the smoothness and the structure of the expected…

机器学习 · 计算机科学 2015-03-09 Richard Combes , Alexandre Proutiere

We consider a resource-aware variant of the classical multi-armed bandit problem: In each round, the learner selects an arm and determines a resource limit. It then observes a corresponding (random) reward, provided the (random) amount of…

机器学习 · 计算机科学 2022-10-18 Viktor Bengs , Eyke Hüllermeier

Thompson sampling provides a solution to bandit problems in which new observations are allocated to arms with the posterior probability that an arm is optimal. While sometimes easy to implement and asymptotically optimal, Thompson sampling…

机器学习 · 计算机科学 2014-10-16 Dean Eckles , Maurits Kaptein