中文
相关论文

相关论文: Regret lower bounds and extended Upper Confidence …

200 篇论文

In this paper, we consider the multi-armed bandit problem with high-dimensional features. First, we prove a minimax lower bound, $\mathcal{O}\big((\log d)^{\frac{\alpha+1}{2}}T^{\frac{1-\alpha}{2}}+\log T\big)$, for the cumulative regret,…

机器学习 · 计算机科学 2021-09-27 Ke Li , Yun Yang , Naveen N. Narisetty

We derive the first finite-time logarithmic Bayes regret upper bounds for Bayesian bandits. In a multi-armed bandit, we obtain $O(c_\Delta \log n)$ and $O(c_h \log^2 n)$ upper bounds for an upper confidence bound algorithm, where $c_h$ and…

机器学习 · 计算机科学 2024-01-23 Alexia Atsidakou , Branislav Kveton , Sumeet Katariya , Constantine Caramanis , Sujay Sanghavi

Upper Confidence Bound (UCB) algorithms are a widely-used class of sequential algorithms for the $K$-armed bandit problem. Despite extensive research over the past decades aimed at understanding their asymptotic and (near) minimax…

统计理论 · 数学 2024-12-10 Qiyang Han , Koulik Khamaru , Cun-Hui Zhang

Multi-armed bandit problems are considered as a paradigm of the trade-off between exploring the environment to find profitable actions and exploiting what is already known. In the stationary case, the distributions of the rewards do not…

统计理论 · 数学 2008-12-18 Aurélien Garivier , Eric Moulines

We present simple and efficient algorithms for the batched stochastic multi-armed bandit and batched stochastic linear bandit problems. We prove bounds for their expected regrets that improve over the best-known regret bounds for any number…

数据结构与算法 · 计算机科学 2020-02-19 Hossein Esfandiari , Amin Karbasi , Abbas Mehrabian , Vahab Mirrokni

We provide a simple method to combine stochastic bandit algorithms. Our approach is based on a "meta-UCB" procedure that treats each of $N$ individual bandit algorithms as arms in a higher-level $N$-armed bandit problem that we solve with a…

机器学习 · 计算机科学 2020-12-25 Ashok Cutkosky , Abhimanyu Das , Manish Purohit

This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least…

机器学习 · 统计学 2011-07-26 Antoine Salomon , Jean-Yves Audibert

We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon. Each arm is associated with an unknown, possibly multi-dimensional distribution, and the merit of an arm…

机器学习 · 计算机科学 2023-01-05 Anmol Kagrecha , Jayakrishnan Nair , Krishna Jagannathan

We study regret minimization in a stochastic multi-armed bandit setting and establish a fundamental trade-off between the regret suffered under an algorithm, and its statistical robustness. Considering broad classes of underlying arms'…

机器学习 · 计算机科学 2020-06-23 Kumar Ashutosh , Jayakrishnan Nair , Anmol Kagrecha , Krishna Jagannathan

The regret lower bound of Lai and Robbins (1985), the gold standard for checking optimality of bandit algorithms, considers arm size fixed as sample size goes to infinity. We show that when arm size increases polynomially with sample size,…

统计理论 · 数学 2019-09-06 Hock Peng Chan , Shouri Hu

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 propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge of the optimal regret, we only require that each base…

机器学习 · 计算机科学 2020-12-25 Aldo Pacchiano , Christoph Dann , Claudio Gentile , Peter Bartlett

We study an extension of standard bandit problem in which there are R layers of experts. Multi-layered experts make selections layer by layer and only the experts in the last layer can play arms. The goal of the learning policy is to…

机器学习 · 计算机科学 2022-08-12 Qihan Guo , Siwei Wang , Jun Zhu

We consider the problem of finitely parameterized multi-armed bandits where the model of the underlying stochastic environment can be characterized based on a common unknown parameter. The true parameter is unknown to the learning agent.…

机器学习 · 计算机科学 2020-11-10 Kishan Panaganti , Dileep Kalathil

We study how to make decisions that minimize Bayesian regret in offline linear bandits. Prior work suggests that one must take actions with maximum lower confidence bound (LCB) on their reward. We argue that the reliance on LCB is…

机器学习 · 计算机科学 2024-07-04 Marek Petrik , Guy Tennenholtz , Mohammad Ghavamzadeh

We study the nonstationary stochastic Multi-Armed Bandit (MAB) problem in which the distribution of rewards associated with each arm are assumed to be time-varying and the total variation in the expected rewards is subject to a variation…

机器学习 · 计算机科学 2021-01-25 Lai Wei , Vaibhav Srivastava

Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration…

机器学习 · 统计学 2019-11-01 Botao Hao , Yasin Abbasi-Yadkori , Zheng Wen , Guang Cheng

One of the key drivers of complexity in the classical (stochastic) multi-armed bandit (MAB) problem is the difference between mean rewards in the top two arms, also known as the instance gap. The celebrated Upper Confidence Bound (UCB)…

机器学习 · 计算机科学 2021-10-27 Anand Kalvit , Assaf Zeevi

The Lipschitz multi-armed bandit (MAB) problem generalizes the classical multi-armed bandit problem by assuming one is given side information consisting of a priori upper bounds on the difference in expected payoff between certain pairs of…

数据结构与算法 · 计算机科学 2009-11-09 Robert Kleinberg , Aleksandrs Slivkins

This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee. In stochastic bandit systems, the rewards may refer to the users' activities, which may…

机器学习 · 计算机科学 2020-07-08 Wenbo Ren , Xingyu Zhou , Jia Liu , Ness B. Shroff
‹ 上一页 1 2 3 10 下一页 ›