中文
相关论文

相关论文: Catoni-Style Change Point Detection for Regret Min…

200 篇论文

We revisit the classic regret-minimization problem in the stochastic multi-armed bandit setting when the arm-distributions are allowed to be heavy-tailed. Regret minimization has been well studied in simpler settings of either bounded…

机器学习 · 计算机科学 2021-02-09 Shubhada Agrawal , Sandeep Juneja , Wouter M. Koolen

Heavy-tailed distributions naturally arise in several settings, from finance to telecommunications. While regret minimization under subgaussian or bounded rewards has been widely studied, learning with heavy-tailed distributions only gained…

机器学习 · 计算机科学 2024-02-13 Gianmarco Genalti , Lupo Marsigli , Nicola Gatti , Alberto Maria Metelli

We consider the setup of stochastic multi-armed bandits in the case when reward distributions are piecewise i.i.d. and bounded with unknown changepoints. We focus on the case when changes happen simultaneously on all arms, and in stark…

机器学习 · 计算机科学 2019-06-10 Subhojyoti Mukherjee , Odalric-Ambrym Maillard

Typical contextual bandit algorithms assume that the rewards at each round lie in some fixed range $[0, R]$, and their regret scales polynomially with this reward range $R$. However, many practical scenarios naturally involve heavy-tailed…

机器学习 · 统计学 2025-02-05 Chenlu Ye , Yujia Jin , Alekh Agarwal , Tong Zhang

The multi-armed bandit problem has been extensively studied under the stationary assumption. However in reality, this assumption often does not hold because the distributions of rewards themselves may change over time. In this paper, we…

机器学习 · 计算机科学 2017-11-22 Fang Liu , Joohyun Lee , Ness Shroff

Stochastic multi-armed bandits (MABs) provide a fundamental reinforcement learning model to study sequential decision making in uncertain environments. The upper confidence bounds (UCB) algorithm gave birth to the renaissance of bandit…

机器学习 · 计算机科学 2024-06-11 Ambrus Tamás , Szabolcs Szentpéteri , Balázs Csanád Csáji

In this paper, we study the problem of stochastic linear bandits with finite action sets. Most of existing work assume the payoffs are bounded or sub-Gaussian, which may be violated in some scenarios such as financial markets. To settle…

机器学习 · 计算机科学 2020-04-29 Bo Xue , Guanghui Wang , Yimu Wang , Lijun Zhang

We study the tail behavior of regret in stochastic multi-armed bandits for algorithms that are asymptotically optimal in expectation. While minimizing expected regret is the classical objective, recent work shows that even such algorithms…

信息论 · 计算机科学 2026-04-17 Subhodip Panda , Shubhada Agrawal

We investigate the non-stationary stochastic linear bandit problem where the reward distribution evolves each round. Existing algorithms characterize the non-stationarity by the total variation budget $B_K$, which is the summation of the…

机器学习 · 计算机科学 2024-03-19 Zhiyong Wang , Jize Xie , Yi Chen , John C. S. Lui , Dongruo Zhou

The stochastic multi-armed bandit problem is well understood when the reward distributions are sub-Gaussian. In this paper we examine the bandit problem under the weaker assumption that the distributions have moments of order 1+\epsilon,…

机器学习 · 统计学 2012-09-11 Sébastien Bubeck , Nicolò Cesa-Bianchi , Gábor Lugosi

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

We study the multi-armed bandit problem where the rewards are realizations of general non-stationary stochastic processes, a setting that generalizes many existing lines of work and analyses. In particular, we present a theoretical analysis…

机器学习 · 计算机科学 2020-09-04 Corinna Cortes , Giulia DeSalvo , Vitaly Kuznetsov , Mehryar Mohri , Scott Yang

Most contextual bandit algorithms minimize regret against the best fixed policy, a questionable benchmark for non-stationary environments that are ubiquitous in applications. In this work, we develop several efficient contextual bandit…

机器学习 · 计算机科学 2019-04-05 Haipeng Luo , Chen-Yu Wei , Alekh Agarwal , John Langford

Classic contextual bandit algorithms for linear models, such as LinUCB, assume that the reward distribution for an arm is modeled by a stationary linear regression. When the linear regression model is non-stationary over time, the regret of…

机器学习 · 统计学 2020-02-14 Qin Ding , Cho-Jui Hsieh , James Sharpnack

We study the optimal trade-off between expectation and tail risk for regret distribution in the stochastic multi-armed bandit model. We fully characterize the interplay among three desired properties for policy design: worst-case…

机器学习 · 统计学 2025-10-27 David Simchi-Levi , Zeyu Zheng , Feng Zhu

In this study, we propose a new method for constructing UCB-type algorithms for stochastic multi-armed bandits based on general convex optimization methods with an inexact oracle. We derive the regret bounds corresponding to the convergence…

机器学习 · 计算机科学 2024-02-13 Yuriy Dorn , Aleksandr Katrutsa , Ilgam Latypov , Andrey Pudovikov

This paper investigates the problem of non-stationary linear bandits, where the unknown regression parameter is evolving over time. Existing studies develop various algorithms and show that they enjoy an…

机器学习 · 计算机科学 2021-12-23 Peng Zhao , Lijun Zhang , Yuan Jiang , Zhi-Hua Zhou

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 introduce Conformal Bandits, a novel framework integrating Conformal Prediction (CP) into bandit problems, a classic paradigm for sequential decision-making under uncertainty. Traditional regret-minimisation bandit strategies like…

机器学习 · 计算机科学 2025-12-11 Simone Cuonzo , Nina Deliu

We investigate the piecewise-stationary combinatorial semi-bandit problem. Compared to the original combinatorial semi-bandit problem, our setting assumes the reward distributions of base arms may change in a piecewise-stationary manner at…

机器学习 · 计算机科学 2020-02-24 Huozhi Zhou , Lingda Wang , Lav R. Varshney , Ee-Peng Lim
‹ 上一页 1 2 3 10 下一页 ›