English
Related papers

Related papers: Off-Policy Evaluation with Out-of-Sample Guarantee…

200 papers

Applications from finance to epidemiology and cyber-security require accurate forecasts of dynamic phenomena, which are often only partially observed. We demonstrate that a system's predictability degrades as a function of temporal…

Computers and Society · Computer Science 2020-01-22 Andrés Abeliuk , Zhishen Huang , Emilio Ferrara , Kristina Lerman

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distribution (OOD) regions. While OOD samples may capture valid…

Artificial Intelligence · Computer Science 2026-05-11 Hongqiang Lin , Dongxu Zhang , Yiding Sun , Mingzhe Li , Ning Yang , Haijun Zhang

Practitioners often use data from a randomized controlled trial to learn a treatment assignment policy that can be deployed on a target population. A recurring concern in doing so is that, even if the randomized trial was well-executed…

Econometrics · Economics 2023-04-25 Lihua Lei , Roshni Sahoo , Stefan Wager

This paper investigates the off-policy evaluation (OPE) problem from a distributional perspective. Rather than focusing solely on the expectation of the total return, as in most existing OPE methods, we aim to estimate the entire return…

Machine Learning · Statistics 2026-04-27 Qi Kuang , Chao Wang , Yuling Jiao , Fan Zhou

Segmented regression is a standard statistical procedure used to estimate the effect of a policy intervention on time series outcomes. This statistical method assumes the normality of the outcome variable, a large sample size, no…

Applications · Statistics 2020-02-18 Mohammad M. Islam , Ph. D. , Erik L. Heiny , Ph. D

Understanding the impact of the most effective policies or treatments on a response variable of interest is desirable in many empirical works in economics, statistics and other disciplines. Due to the widespread winner's curse phenomenon,…

Methodology · Statistics 2022-10-25 Waverly Wei , Yuqing Zhou , Zeyu Zheng , Jingshen Wang

Evaluating and optimizing policies in the presence of unobserved confounders is a problem of growing interest in offline reinforcement learning. Using conventional methods for offline RL in the presence of confounding can not only lead to…

Machine Learning · Statistics 2023-11-08 Chinmaya Kausik , Yangyi Lu , Kevin Tan , Maggie Makar , Yixin Wang , Ambuj Tewari

The goal of machine learning is to find models that minimize prediction error on data that has not yet been seen. Its operational paradigm assumes access to a dataset $S$ and articulates a scheme for evaluating how well a given model…

Machine Learning · Computer Science 2026-04-22 Maxim Raginsky , Benjamin Recht

We address the problem of uncertainty quantification and propose measures of total, aleatoric, and epistemic uncertainty based on a known decomposition of (strictly) proper scoring rules, a specific type of loss function, into a divergence…

Machine Learning · Computer Science 2025-05-29 Paul Hofman , Yusuf Sale , Eyke Hüllermeier

Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Laura O'Mahony , David JP O'Sullivan , Nikola S. Nikolov

Offline reinforcement learning, wherein one uses off-policy data logged by a fixed behavior policy to evaluate and learn new policies, is crucial in applications where experimentation is limited such as medicine. We study the estimation of…

Machine Learning · Computer Science 2020-06-09 Nathan Kallus , Masatoshi Uehara

This paper considers the problem of determining an optimal control action based on observed data. We formulate the problem assuming that the system can be modelled by a nonlinear state-space model, but where the model parameters, state and…

Optimization and Control · Mathematics 2021-07-02 Johannes N. Hendriks , James R. Z. Holdsworth , Adrian G. Wills , Thomas B. Schon , Brett Ninness

Time-of-flight measurements such as the OPERA and MINOS experiments rely crucially on statistical analysis (as well as many other ingredients) for their conclusions. The nature of these experiments leads to a simple class of statistical…

High Energy Physics - Experiment · Physics 2011-11-02 Oliver Riordan , Alex Selby

We study high-confidence off-policy evaluation in the context of infinite-horizon Markov decision processes, where the objective is to establish a confidence interval (CI) for the target policy value using only offline data pre-collected…

Machine Learning · Statistics 2023-10-03 Wenzhuo Zhou , Yuhan Li , Ruoqing Zhu , Annie Qu

We consider off-policy evaluation of dynamic treatment rules under sequential ignorability, given an assumption that the underlying system can be modeled as a partially observed Markov decision process (POMDP). We propose an estimator,…

Machine Learning · Computer Science 2023-05-10 Yuchen Hu , Stefan Wager

Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the…

Machine Learning · Computer Science 2022-11-23 Jiachen Li , Shuo Cheng , Zhenyu Liao , Huayan Wang , William Yang Wang , Qinxun Bai

In data analysis, unexpected results often prompt researchers to revisit their procedures to identify potential issues. While some researchers may struggle to identify the root causes, experienced researchers can often quickly diagnose…

Methodology · Statistics 2026-01-06 H. Sherry Zhang , Roger D. Peng

Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end…

Machine Learning · Computer Science 2022-06-22 Yue Jin , Yue Zhang , Tao Qin , Xudong Zhang , Jian Yuan , Houqiang Li , Tie-Yan Liu

A generic out-of-sample error estimate is proposed for robust $M$-estimators regularized with a convex penalty in high-dimensional linear regression where $(X,y)$ is observed and $p,n$ are of the same order. If $\psi$ is the derivative of…

Statistics Theory · Mathematics 2023-03-31 Pierre C Bellec