English
Related papers

Related papers: Doubly robust off-policy evaluation with shrinkage

200 papers

We propose a linear contextual bandit algorithm with $O(\sqrt{dT\log T})$ regret bound, where $d$ is the dimension of contexts and $T$ isthe time horizon. Our proposed algorithm is equipped with a novel estimator in which exploration is…

Machine Learning · Statistics 2023-03-30 Wonyoung Kim , Myunghee Cho Paik , Min-hwan Oh

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

Motivated by the poor performance of cross-validation in settings where data are scarce, we propose a novel estimator of the out-of-sample performance of a policy in data-driven optimization.Our approach exploits the optimization problem's…

Optimization and Control · Mathematics 2022-08-04 Vishal Gupta , Michael Huang , Paat Rusmevichientong

We propose the first boosting algorithm for off-policy learning from logged bandit feedback. Unlike existing boosting methods for supervised learning, our algorithm directly optimizes an estimate of the policy's expected reward. We analyze…

Machine Learning · Computer Science 2023-05-03 Ben London , Levi Lu , Ted Sandler , Thorsten Joachims

Off-policy evaluation and learning in contextual bandits use logged interaction data to estimate and optimize the value of a target policy. Most existing methods require sufficient action overlap between the logging and target policies, and…

Machine Learning · Statistics 2026-02-03 Shu Tamano

Doubly robust methods hold considerable promise for off-policy evaluation in Markov decision processes (MDPs) under sequential ignorability: They have been shown to converge as $1/\sqrt{T}$ with the horizon $T$, to be statistically…

Machine Learning · Statistics 2025-09-30 Mohammad Mehrabi , Stefan Wager

In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new…

Machine Learning · Computer Science 2019-11-06 Ofir Nachum , Yinlam Chow , Bo Dai , Lihong Li

We consider the problem of robustly predicting as well as the best linear combination of $d$ given functions in least squares regression, and variants of this problem including constraints on the parameters of the linear combination. For…

Statistics Theory · Mathematics 2012-02-24 Jean-Yves Audibert , Olivier Catoni

We propose a new framework for contextual multi-armed bandits based on tree ensembles. Our framework adapts two widely used bandit methods, Upper Confidence Bound and Thompson Sampling, for both standard and combinatorial settings. As part…

Machine Learning · Computer Science 2025-12-04 Hannes Nilsson , Rikard Johansson , Niklas Åkerblom , Morteza Haghir Chehreghani

We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value…

Machine Learning · Computer Science 2020-02-19 Omer Gottesman , Yao Liu , Scott Sussex , Emma Brunskill , Finale Doshi-Velez

We develop confidence bounds that hold uniformly over time for off-policy evaluation in the contextual bandit setting. These confidence sequences are based on recent ideas from martingale analysis and are non-asymptotic, non-parametric, and…

Machine Learning · Computer Science 2021-02-19 Nikos Karampatziakis , Paul Mineiro , Aaditya Ramdas

We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even…

Machine Learning · Computer Science 2019-12-17 Weihao Kong , Gregory Valiant , Emma Brunskill

In extreme value theory and other related risk analysis fields, probability weighted moments (PWM) have been frequently used to estimate the parameters of classical extreme value distributions. This method-of-moment technique can be applied…

Statistics Theory · Mathematics 2023-06-21 Anna Ben-Hamou , Philippe Naveau , Maud Thomas

We consider Bayesian optimization in settings where observations can be adversarially biased, for example by an uncontrolled hidden confounder. Our first contribution is a reduction of the confounded setting to the dueling bandit model.…

Machine Learning · Statistics 2021-06-10 Johannes Kirschner , Andreas Krause

Distributionally robust policy learning aims to find a policy that performs well under the worst-case distributional shift, and yet most existing methods for robust policy learning consider the worst-case joint distribution of the covariate…

Machine Learning · Computer Science 2025-06-03 Jingyuan Wang , Zhimei Ren , Ruohan Zhan , Zhengyuan Zhou

We study the linear contextual bandit problem in the presence of adversarial corruption, where the reward at each round is corrupted by an adversary, and the corruption level (i.e., the sum of corruption magnitudes over the horizon) is…

Machine Learning · Computer Science 2022-07-12 Jiafan He , Dongruo Zhou , Tong Zhang , Quanquan Gu

This paper constructs improved estimators of the means in the Gaussian saturated one-way layout with an ordinal factor. The least squares estimator for the mean vector in this saturated model is usually inadmissible. The hybrid shrinkage…

Statistics Theory · Mathematics 2007-06-13 Rudolf Beran

We study bandit convex optimization methods that adapt to the norm of the comparator, a topic that has only been studied before for its full-information counterpart. Specifically, we develop convex bandit algorithms with regret bounds that…

Machine Learning · Computer Science 2020-07-17 Dirk van der Hoeven , Ashok Cutkosky , Haipeng Luo

A robust estimation framework for binary regression models is studied, aiming to extend traditional approaches like logistic regression models. While previous studies largely focused on logistic models, we explore a broader class of models…

Methodology · Statistics 2025-02-24 Kenichi Hayashi , Shinto Eguchi

We introduce a trimmed version of the Hill estimator for the index of a heavy-tailed distribution, which is robust to perturbations in the extreme order statistics. In the ideal Pareto setting, the estimator is essentially finite-sample…

Methodology · Statistics 2017-11-15 Shrijita Bhattacharya , Michael Kallitsis , Stilian Stoev
‹ Prev 1 4 5 6 7 8 10 Next ›