English
Related papers

Related papers: Offline Contextual Bandits with Overparameterized …

200 papers

We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood techniques to formulate our estimator and confidence…

Machine Learning · Computer Science 2020-10-20 Nikos Karampatziakis , John Langford , Paul Mineiro

We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic policies in contextual bandits with continuous action spaces. Our work is motivated by practical scenarios where the target policy needs to be…

Machine Learning · Computer Science 2022-12-29 Haanvid Lee , Jongmin Lee , Yunseon Choi , Wonseok Jeon , Byung-Jun Lee , Yung-Kyun Noh , Kee-Eung Kim

We study an online decision making problem where on each round a learner chooses a list of items based on some side information, receives a scalar feedback value for each individual item, and a reward that is linearly related to this…

Machine Learning · Computer Science 2016-11-07 Akshay Krishnamurthy , Alekh Agarwal , Miroslav Dudik

We introduce the cram method as a general statistical framework for evaluating the final learned policy from a multi-armed contextual bandit algorithm, using the dataset generated by the same bandit algorithm. The proposed on-policy…

Machine Learning · Computer Science 2025-04-16 Zeyang Jia , Kosuke Imai , Michael Lingzhi Li

Contextual bandits with average-case statistical guarantees are inadequate in risk-averse situations because they might trade off degraded worst-case behaviour for better average performance. Designing a risk-averse contextual bandit is…

Machine Learning · Statistics 2023-07-11 Mónika Farsang , Paul Mineiro , Wangda Zhang

The statistical framework of Generalized Linear Models (GLM) can be applied to sequential problems involving categorical or ordinal rewards associated, for instance, with clicks, likes or ratings. In the example of binary rewards, logistic…

Machine Learning · Computer Science 2020-03-24 Yoan Russac , Olivier Cappé , Aurélien Garivier

We consider offline policy optimization (OPO) in contextual bandits, where one is given a fixed dataset of logged interactions. While pessimistic regularizers are typically used to mitigate distribution shift, prior implementations thereof…

Machine Learning · Computer Science 2023-10-27 Lequn Wang , Akshay Krishnamurthy , Aleksandrs Slivkins

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Machine Learning · Computer Science 2023-07-25 Ayush Sekhari , Karthik Sridharan , Wen Sun , Runzhe Wu

A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. The primary goal of the agent is to identify the latent state, after which it can act optimally.…

Machine Learning · Computer Science 2020-06-17 Joey Hong , Branislav Kveton , Manzil Zaheer , Yinlam Chow , Amr Ahmed , Craig Boutilier

The stochastic contextual bandit problem, which models the trade-off between exploration and exploitation, has many real applications, including recommender systems, online advertising and clinical trials. As many other machine learning…

Machine Learning · Statistics 2022-06-14 Qin Ding , Yue Kang , Yi-Wei Liu , Thomas C. M. Lee , Cho-Jui Hsieh , James Sharpnack

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions,…

Machine Learning · Statistics 2020-06-23 Akshay Krishnamurthy , John Langford , Aleksandrs Slivkins , Chicheng Zhang

The feedback that AI systems (e.g., recommender systems, chatbots) collect from user interactions is a crucial source of training data. While short-term feedback (e.g., clicks, engagement) is widely used for training, there is ample…

Machine Learning · Computer Science 2025-05-29 Richa Rastogi , Yuta Saito , Thorsten Joachims

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in…

Machine Learning · Computer Science 2017-06-20 Lihong Li , Yu Lu , Dengyong Zhou

We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy the best controller for the unknown system by periodically selecting among a collection of $N$ candidate…

Optimization and Control · Mathematics 2026-03-19 Haoyuan Sun , Ali Jadbabaie

In production systems, contextual bandit approaches often rely on direct reward models that take both action and context as input. However, these models can suffer from confounding, making it difficult to isolate the effect of the action…

Machine Learning · Computer Science 2025-09-16 Alexandre Gilotte , Otmane Sakhi , Imad Aouali , Benjamin Heymann

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult…

Machine Learning · Statistics 2018-12-18 Maria Dimakopoulou , Zhengyuan Zhou , Susan Athey , Guido Imbens

In the classical multi-armed bandit problem, instance-dependent algorithms attain improved performance on "easy" problems with a gap between the best and second-best arm. Are similar guarantees possible for contextual bandits? While…

Machine Learning · Computer Science 2020-10-08 Dylan J. Foster , Alexander Rakhlin , David Simchi-Levi , Yunzong Xu

This paper addresses the poor finite-horizon performance of existing online \emph{restless bandit} (RB) algorithms, which stems from the prohibitive sample complexity of learning a full \emph{Markov decision process} (MDP) for each agent.…

Machine Learning · Computer Science 2026-04-07 Jiamin Xu , Ivan Nazarov , Aditya Rastogi , África Periáñez , Kyra Gan

Contextual bandits serve as a fundamental model for many sequential decision making tasks. The most popular theoretically justified approaches are based on the optimism principle. While these algorithms can be practical, they are known to…

Machine Learning · Computer Science 2020-03-17 Botao Hao , Tor Lattimore , Csaba Szepesvari

In many bandit problems, the maximal reward achievable by a policy is often unknown in advance. We consider the problem of estimating the optimal policy value in the sublinear data regime before the optimal policy is even learnable. We…

Machine Learning · Computer Science 2023-02-21 Jonathan N. Lee , Weihao Kong , Aldo Pacchiano , Vidya Muthukumar , Emma Brunskill