中文
相关论文

相关论文: Taming the Monster Every Context: Complexity Measu…

200 篇论文

We consider the general (stochastic) contextual bandit problem under the realizability assumption, i.e., the expected reward, as a function of contexts and actions, belongs to a general function class $\mathcal{F}$. We design a fast and…

机器学习 · 计算机科学 2021-07-13 David Simchi-Levi , Yunzong Xu

Computationally efficient contextual bandits are often based on estimating a predictive model of rewards given contexts and arms using past data. However, when the reward model is not well-specified, the bandit algorithm may incur…

机器学习 · 计算机科学 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access…

机器学习 · 计算机科学 2014-10-15 Alekh Agarwal , Daniel Hsu , Satyen Kale , John Langford , Lihong Li , Robert E. Schapire

A major research direction in contextual bandits is to develop algorithms that are computationally efficient, yet support flexible, general-purpose function approximation. Algorithms based on modeling rewards have shown strong empirical…

机器学习 · 计算机科学 2021-07-14 Dylan J. Foster , Claudio Gentile , Mehryar Mohri , Julian Zimmert

We study the $K$-armed contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes \emph{preference-based feedback} suggesting that one…

机器学习 · 计算机科学 2021-11-25 Aadirupa Saha , Akshay Krishnamurthy

We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal…

机器学习 · 计算机科学 2011-06-17 Miroslav Dudik , Daniel Hsu , Satyen Kale , Nikos Karampatziakis , John Langford , Lev Reyzin , Tong Zhang

Designing efficient general-purpose contextual bandit algorithms that work with large -- or even continuous -- action spaces would facilitate application to important scenarios such as information retrieval, recommendation systems, and…

机器学习 · 计算机科学 2022-07-14 Yinglun Zhu , Paul Mineiro

We give an oracle-based algorithm for the adversarial contextual bandit problem, where either contexts are drawn i.i.d. or the sequence of contexts is known a priori, but where the losses are picked adversarially. Our algorithm is…

机器学习 · 计算机科学 2016-06-02 Vasilis Syrgkanis , Haipeng Luo , Akshay Krishnamurthy , Robert E. Schapire

We provide the first oracle efficient sublinear regret algorithms for adversarial versions of the contextual bandit problem. In this problem, the learner repeatedly makes an action on the basis of a context and receives reward for the…

机器学习 · 计算机科学 2016-02-09 Vasilis Syrgkanis , Akshay Krishnamurthy , Robert E. Schapire

Combinatorial multi-armed bandits provide a fundamental online decision-making environment where a decision-maker interacts with an environment across $T$ time steps, each time selecting an action and learning the cost of that action. The…

机器学习 · 计算机科学 2026-04-13 Gerdus Benadè , Rathish Das , Thomas Lavastida

We propose the first contextual bandit algorithm that is parameter-free, efficient, and optimal in terms of dynamic regret. Specifically, our algorithm achieves dynamic regret $\mathcal{O}(\min\{\sqrt{ST},…

机器学习 · 计算机科学 2019-06-19 Yifang Chen , Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei

We present an oracle-efficient relaxation for the adversarial contextual bandits problem, where the contexts are sequentially drawn i.i.d from a known distribution and the cost sequence is chosen by an online adversary. Our algorithm has a…

机器学习 · 计算机科学 2023-11-13 Kiarash Banihashem , MohammadTaghi Hajiaghayi , Suho Shin , Max Springer

We consider a multi-armed bandit problem where payoffs are a linear function of an observed stochastic contextual variable. In the scenario where there exists a gap between optimal and suboptimal rewards, several algorithms have been…

数据结构与算法 · 计算机科学 2014-07-08 José Bento , Stratis Ioannidis , S. Muthukrishnan , Jinyun Yan

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

We consider the problem of online regret minimization in linear bandits with access to prior observations (offline data) from the underlying bandit model. There are numerous applications where extensive offline data is often available, such…

机器学习 · 计算机科学 2026-05-13 Sushant Vijayan , Arun Suggala , Karthikeyan Shanmugam , Soumyabrata Pal

We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret $\mathcal{O}(\sqrt{T})$ for learning over $T$ rounds, when the total…

机器学习 · 计算机科学 2020-10-16 Chen-Yu Wei , Haipeng Luo , Alekh Agarwal

We study the Logistic Contextual Slate Bandit problem, where, at each round, an agent selects a slate of $N$ items from an exponentially large set (of size $2^{\Omega(N)}$) of candidate slates provided by the environment. A single binary…

机器学习 · 计算机科学 2026-05-13 Tanmay Goyal , Gaurav Sinha

This paper investigates regret minimization, statistical inference, and their interplay in high-dimensional online decision-making based on the sparse linear context bandit model. We integrate the $\varepsilon$-greedy bandit algorithm for…

机器学习 · 计算机科学 2025-05-20 Congyuan Duan , Wanteng Ma , Jiashuo Jiang , Dong Xia

We study a generalization of the problem of online learning in adversarial linear contextual bandits by incorporating loss functions that belong to a reproducing kernel Hilbert space, which allows for a more flexible modeling of complex…

机器学习 · 统计学 2023-10-04 Gergely Neu , Julia Olkhovskaya , Sattar Vakili

Bandit optimization is a difficult problem, especially if the reward model is high-dimensional. When rewards are modeled by neural networks, sublinear regret has only been shown under strong assumptions, usually when the network is…

机器学习 · 计算机科学 2025-01-14 Mikhail Terekhov
‹ 上一页 1 2 3 10 下一页 ›