English
Related papers

Related papers: No-Regret Algorithms for Time-Varying Bayesian Opt…

200 papers

This work theoretically studies a ubiquitous reinforcement learning policy for controlling the canonical model of continuous-time stochastic linear-quadratic systems. We show that randomized certainty equivalent policy addresses the…

Machine Learning · Computer Science 2022-08-23 Mohamad Kazem Shirani Faradonbeh

Black box optimisation of an unknown function from expensive and noisy evaluations is a ubiquitous problem in machine learning, academic research and industrial production. An abstraction of the problem can be formulated as a kernel based…

Machine Learning · Statistics 2023-02-02 Sattar Vakili , Danyal Ahmed , Alberto Bernacchia , Ciara Pike-Burke

We consider the $\epsilon$-greedy strategy for the multi-arm bandit with covariates (MABC) problem, where the mean reward functions are assumed to lie in a reproducing kernel Hilbert space (RKHS). We propose to estimate the unknown mean…

Machine Learning · Statistics 2025-06-03 Sakshi Arya , Bharath K. Sriperumbudur

We develop a new approach to obtaining high probability regret bounds for online learning with bandit feedback against an adaptive adversary. While existing approaches all require carefully constructing optimistic and biased loss…

Machine Learning · Computer Science 2020-11-02 Chung-Wei Lee , Haipeng Luo , Chen-Yu Wei , Mengxiao Zhang

We motivate and analyse a new Tree Search algorithm, GPTS, based on recent theoretical advances in the use of Gaussian Processes for Bandit problems. We consider tree paths as arms and we assume the target/reward function is drawn from a GP…

Machine Learning · Computer Science 2011-01-18 Louis Dorard , John Shawe-Taylor

We study the problem of \emph{dynamic regret minimization} in $K$-armed Dueling Bandits under non-stationary or time varying preferences. This is an online learning setup where the agent chooses a pair of items at each round and observes…

Machine Learning · Computer Science 2022-06-14 Aadirupa Saha , Shubham Gupta

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…

Machine Learning · Computer Science 2020-02-18 Lingda Wang , Huozhi Zhou , Bingcong Li , Lav R. Varshney , Zhizhen Zhao

In this work, we investigate black-box optimization from the perspective of frequentist kernel methods. We propose a novel batch optimization algorithm, which jointly maximizes the acquisition function and select points from a whole batch…

Machine Learning · Computer Science 2020-03-30 Yueming Lyu , Yuan Yuan , Ivor W. Tsang

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…

Machine Learning · Computer Science 2025-05-20 Congyuan Duan , Wanteng Ma , Jiashuo Jiang , Dong Xia

We consider stochastic non-stationary linear bandits where the linear parameter connecting contexts to the reward changes over time. Existing algorithms in this setting localize the policy by gradually discarding or down-weighting past…

Machine Learning · Statistics 2026-03-05 Margherita Lazzaretto , Jonas Peters , Niklas Pfister

We revisit the challenge of designing online algorithms for the bandit convex optimization problem (BCO) which are also scalable to high dimensional problems. Hence, we consider algorithms that are \textit{projection-free}, i.e., based on…

Machine Learning · Computer Science 2019-10-09 Dan Garber , Ben Kretzu

Algorithm selection is typically based on models of algorithm performance, learned during a separate offline training sequence, which can be prohibitively expensive. In recent work, we adopted an online approach, in which a performance…

Artificial Intelligence · Computer Science 2013-01-31 Matteo Gagliolo , Juergen Schmidhuber

We present safe control of partially-observed linear time-varying systems in the presence of unknown and unpredictable process and measurement noise. We introduce a control algorithm that minimizes dynamic regret, i.e., that minimizes the…

Systems and Control · Electrical Eng. & Systems 2023-04-03 Hongyu Zhou , Vasileios Tzoumas

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…

Machine Learning · Computer Science 2024-02-13 Yuriy Dorn , Aleksandr Katrutsa , Ilgam Latypov , Andrey Pudovikov

Online bilevel optimization (OBO) is a powerful framework for machine learning problems where both outer and inner objectives evolve over time, requiring dynamic updates. Current OBO approaches rely on deterministic \textit{window-smoothed}…

Machine Learning · Computer Science 2026-05-20 Parvin Nazari , Bojian Hou , Davoud Ataee Tarzanagh , Li Shen , George Michailidis

In many application domains (e.g., recommender systems, intelligent tutoring systems), the rewards associated to the actions tend to decrease over time. This decay is either caused by the actions executed in the past (e.g., a user may get…

Machine Learning · Statistics 2026-04-24 Julien Seznec , Pierre Ménard , Alessandro Lazaric , Michal Valko

We study the stochastic contextual bandit problem, where the reward is generated from an unknown function with additive noise. No assumption is made about the reward function other than boundedness. We propose a new algorithm, NeuralUCB,…

Machine Learning · Computer Science 2020-07-03 Dongruo Zhou , Lihong Li , Quanquan Gu

We study dynamic regret minimization in unconstrained adversarial linear bandit problems. In this setting, a learner must minimize the cumulative loss relative to an arbitrary sequence of comparators…

Machine Learning · Computer Science 2026-03-30 Alberto Rumi , Andrew Jacobsen , Nicolò Cesa-Bianchi , Fabio Vitale

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 consider control of uncertain linear time-varying stochastic systems from the perspective of regret minimization. Specifically, we focus on the problem of designing a feedback controller that minimizes the loss relative to a clairvoyant…

Systems and Control · Electrical Eng. & Systems 2024-07-04 Andrea Martin , Luca Furieri , Florian Dörfler , John Lygeros , Giancarlo Ferrari-Trecate