English
Related papers

Related papers: Variance-Dependent Regret Lower Bounds for Context…

200 papers

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…

Machine Learning · Computer Science 2019-04-05 Haipeng Luo , Chen-Yu Wei , Alekh Agarwal , John Langford

Motivated by modern applications, such as online advertisement and recommender systems, we study the top-$k$ extreme contextual bandits problem, where the total number of arms can be enormous, and the learner is allowed to select $k$ arms…

Machine Learning · Statistics 2021-02-17 Rajat Sen , Alexander Rakhlin , Lexing Ying , Rahul Kidambi , Dean Foster , Daniel Hill , Inderjit Dhillon

We present the first high-probability optimal regret bound for a policy optimization technique applied to the problem of stochastic contextual multi-armed bandit (CMAB) with general offline function approximation. Our algorithm is both…

Machine Learning · Computer Science 2026-02-17 Orin Levy , Yishay Mansour

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…

Machine Learning · Computer Science 2021-06-14 Sanath Kumar Krishnamurthy , Vitor Hadad , Susan Athey

We provide a unified algorithmic framework for ensemble sampling in nonlinear contextual bandits and develop corresponding regret bounds for two most common nonlinear contextual bandit settings: Generalized Linear Ensemble Sampling (GLM-ES)…

Machine Learning · Computer Science 2026-05-12 Jiazheng Sun , Weixin Wang , Pan Xu

We introduce the problem of regret minimization in Adversarial Dueling Bandits. As in classic Dueling Bandits, the learner has to repeatedly choose a pair of items and observe only a relative binary `win-loss' feedback for this pair, but…

Machine Learning · Computer Science 2020-10-29 Aadirupa Saha , Tomer Koren , Yishay Mansour

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…

Machine Learning · Computer Science 2021-07-14 Dylan J. Foster , Claudio Gentile , Mehryar Mohri , Julian Zimmert

We develop parameter-free algorithms for unconstrained online learning with regret guarantees that scale with the gradient variation $V_T(u) = \sum_{t=2}^T \|\nabla f_t(u)-\nabla f_{t-1}(u)\|^2$. For $L$-smooth convex loss, we provide…

Machine Learning · Computer Science 2026-04-14 Yuheng Zhao , Andrew Jacobsen , Nicolò Cesa-Bianchi , Peng Zhao

We derive near-optimal per-action regret bounds for sleeping bandits, in which both the sets of available arms and their losses in every round are chosen by an adversary. In a setting with $K$ total arms and at most $A$ available arms in…

Machine Learning · Computer Science 2024-05-31 Quan Nguyen , Nishant A. Mehta

We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that reduces contextual bandit learning with general reward function approximation to offline regression. The framework allows near-optimal regret for contextual…

Machine Learning · Computer Science 2026-02-11 Hao Qin , Chicheng Zhang

We study a $K$-armed non-stationary bandit model where rewards change smoothly, as captured by H\"{o}lder class assumptions on rewards as functions of time. Such smooth changes are parametrized by a H\"{o}lder exponent $\beta$ and…

Machine Learning · Statistics 2025-02-27 Joe Suk

The problem of reinforcement learning in an unknown and discrete Markov Decision Process (MDP) under the average-reward criterion is considered, when the learner interacts with the system in a single stream of observations, starting from an…

Machine Learning · Statistics 2018-03-06 Mohammad Sadegh Talebi , Odalric-Ambrym Maillard

We study a bandit version of phase retrieval where the learner chooses actions $(A_t)_{t=1}^n$ in the $d$-dimensional unit ball and the expected reward is $\langle A_t, \theta_\star\rangle^2$ where $\theta_\star \in \mathbb R^d$ is an…

Machine Learning · Statistics 2021-06-07 Tor Lattimore , Botao Hao

Contextual bandits are a central framework for sequential decision-making, with applications ranging from recommendation systems to clinical trials. While nonparametric methods can flexibly model complex reward structures, they suffer from…

Statistics Theory · Mathematics 2026-01-01 Wanteng Ma , T. Tony Cai

This study investigates the problem of $K$-armed linear contextual bandits, an instance of the multi-armed bandit problem, under an adversarial corruption. At each round, a decision-maker observes an independent and identically distributed…

Machine Learning · Computer Science 2023-12-29 Masahiro Kato , Shinji Ito

High-dimensional linear bandits with low-dimensional structure have received considerable attention in recent studies due to their practical significance. The most common structure in the literature is sparsity. However, it may not be…

Machine Learning · Statistics 2026-01-01 Nam Phuong Tran , The Anh Ta , Debmalya Mandal , Long Tran-Thanh

Bandits with knapsacks (BwK) constitute a fundamental model that combines aspects of stochastic integer programming with online learning. Classical algorithms for BwK with a time horizon $T$ achieve a problem-independent regret bound of…

Quantum Physics · Physics 2025-07-08 Yuexin Su , Ziyi Yang , Peiyuan Huang , Tongyang Li , Yinyu Ye

We study the $K$-armed dueling bandit problem, a variation of the traditional multi-armed bandit problem in which feedback is obtained in the form of pairwise comparisons. Previous learning algorithms have focused on the $\textit{fully…

Machine Learning · Computer Science 2022-09-27 Arpit Agarwal , Rohan Ghuge , Viswanath Nagarajan

We study the problem of expert advice under partial bandit feedback setting and create a sequential minimax optimal algorithm. Our algorithm works with a more general partial monitoring setting, where, in contrast to the classical bandit…

Machine Learning · Computer Science 2022-04-15 Kaan Gokcesu , Hakan Gokcesu

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…

Machine Learning · Computer Science 2014-10-15 Alekh Agarwal , Daniel Hsu , Satyen Kale , John Langford , Lihong Li , Robert E. Schapire