English
Related papers

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

200 papers

We consider a budget-constrained bandit problem where each arm pull incurs a random cost, and yields a random reward in return. The objective is to maximize the total expected reward under a budget constraint on the total cost. The model is…

Machine Learning · Computer Science 2020-03-03 Semih Cayci , Atilla Eryilmaz , R. Srikant

In this paper, we investigate the stochastic contextual bandit with general function space and graph feedback. We propose an algorithm that addresses this problem by adapting to both the underlying graph structures and reward gaps. To the…

Machine Learning · Computer Science 2024-01-09 Xueping Gong , Jiheng Zhang

We study the $\textit{single-index bandit}$ problem, where rewards depend on an unknown one-dimensional projection of high-dimensional contexts through an unknown reward function. This model extends linear and generalized linear bandits to…

Machine Learning · Statistics 2026-05-12 Devdan Dey , Sujoy Bhore , Avishek Ghosh

We study the constrained variant of the \emph{multi-armed bandit} (MAB) problem, in which the learner aims not only at minimizing the total loss incurred during the learning dynamic, but also at controlling the violation of multiple…

Machine Learning · Computer Science 2026-02-17 Francesco Emanuele Stradi , Kalana Kalupahana , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

As sequential learning algorithms are increasingly applied to real life, ensuring data privacy while maintaining their utilities emerges as a timely question. In this context, regret minimisation in stochastic bandits under…

Machine Learning · Statistics 2025-05-12 Achraf Azize , Yulian Wu , Junya Honda , Francesco Orabona , Shinji Ito , Debabrota Basu

We study small-loss bounds for adversarial multi-armed bandits with graph feedback, that is, adaptive regret bounds that depend on the loss of the best arm or related quantities, instead of the total number of rounds. We derive the first…

Machine Learning · Computer Science 2020-06-24 Chung-Wei Lee , Haipeng Luo , Mengxiao Zhang

We study reinforcement learning with linear function approximation and adversarially changing cost functions, a setup that has mostly been considered under simplifying assumptions such as full information feedback or exploratory…

Machine Learning · Computer Science 2023-01-31 Uri Sherman , Tomer Koren , Yishay Mansour

This paper analyses the problem of Gaussian process (GP) bandits with deterministic observations. The analysis uses a branch and bound algorithm that is related to the UCB algorithm of (Srinivas et al., 2010). For GPs with Gaussian…

Machine Learning · Computer Science 2012-03-12 Nando de Freitas , Alex Smola , Masrour Zoghi

We study the problem of stochastic contextual bandits in the agnostic setting, where the goal is to compete with the best policy in a given class without assuming realizability or imposing model restrictions on losses or rewards. In this…

Machine Learning · Statistics 2026-04-06 Samuel Girard , Aurelien Bibaut , Arthur Gretton , Nathan Kallus , Houssam Zenati

We present a non-asymptotic lower bound on the eigenspectrum of the design matrix generated by any linear bandit algorithm with sub-linear regret when the action set has well-behaved curvature. Specifically, we show that the minimum…

Machine Learning · Computer Science 2023-01-10 Debangshu Banerjee , Avishek Ghosh , Sayak Ray Chowdhury , Aditya Gopalan

We prove that Thompson sampling exhibits $\tilde{O}(\sigma d \sqrt{T} + d r \sqrt{\mathrm{Tr}(\Sigma_0)})$ Bayesian regret in the linear-Gaussian bandit with a $\mathcal{N}(\mu_0, \Sigma_0)$ prior distribution on the coefficients, where $d$…

Machine Learning · Computer Science 2026-01-06 Yifan Zhu , John C. Duchi , Benjamin Van Roy

In this paper we initiate a study of non parametric contextual bandits under shape constraints on the mean reward function. Specifically, we study a setting where the context is one dimensional, and the mean reward function is isotonic with…

Statistics Theory · Mathematics 2021-10-22 Sabyasachi Chatterjee , Subhabrata Sen

We consider combinatorial online learning with subset choices when only relative feedback information from subsets is available, instead of bandit or semi-bandit feedback which is absolute. Specifically, we study two regret minimisation…

Machine Learning · Computer Science 2020-02-28 Aadirupa Saha , Aditya Gopalan

We study the generalized linear contextual bandit problem within the constraints of limited adaptivity. In this paper, we present two algorithms, $\texttt{B-GLinCB}$ and $\texttt{RS-GLinCB}$, that address, respectively, two prevalent…

Machine Learning · Computer Science 2025-10-29 Ayush Sawarni , Nirjhar Das , Siddharth Barman , Gaurav Sinha

By leveraging the representation power of deep neural networks, neural upper confidence bound (UCB) algorithms have shown success in contextual bandits. To further balance the exploration and exploitation, we propose…

Machine Learning · Computer Science 2025-03-12 Ha Manh Bui , Enrique Mallada , Anqi Liu

In this paper, we investigate the streaming bandits problem, wherein the learner aims to minimize regret by dealing with online arriving arms and sublinear arm memory. We establish the tight worst-case regret lower bound of $\Omega \left(…

Machine Learning · Computer Science 2023-06-14 Shaoang Li , Lan Zhang , Junhao Wang , Xiang-Yang Li

We consider the adversarial convex bandit problem and we build the first $\mathrm{poly}(T)$-time algorithm with $\mathrm{poly}(n) \sqrt{T}$-regret for this problem. To do so we introduce three new ideas in the derivative-free optimization…

Machine Learning · Computer Science 2016-07-19 Sébastien Bubeck , Ronen Eldan , Yin Tat Lee

We consider the contextual bandit problem where at each time, the agent only has access to a noisy version of the context and the error variance (or an estimator of this variance). This setting is motivated by a wide range of applications…

Machine Learning · Statistics 2024-03-19 Yongyi Guo , Ziping Xu , Susan Murphy

Conservative Contextual Bandits (CCBs) address safety in sequential decision making by requiring that an agent's policy, along with minimizing regret, also satisfies a safety constraint: the performance is not worse than a baseline policy…

Machine Learning · Computer Science 2024-12-10 Rohan Deb , Mohammad Ghavamzadeh , Arindam Banerjee

We study the stochastic shortest path problem with adversarial costs and known transition, and show that the minimax regret is $\widetilde{O}(\sqrt{DT^\star K})$ and $\widetilde{O}(\sqrt{DT^\star SA K})$ for the full-information setting and…

Machine Learning · Computer Science 2021-06-23 Liyu Chen , Haipeng Luo , Chen-Yu Wei