English
Related papers

Related papers: Adaptive Off-Policy Inference for M-Estimators Und…

200 papers

Estimation and inference in statistics pose significant challenges when data are collected adaptively. Even in linear models, the Ordinary Least Squares (OLS) estimator may fail to exhibit asymptotic normality for single coordinate…

Statistics Theory · Mathematics 2023-10-31 Licong Lin , Mufang Ying , Suvrojit Ghosh , Koulik Khamaru , Cun-Hui Zhang

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

When data is collected in an adaptive manner, even simple methods like ordinary least squares can exhibit non-normal asymptotic behavior. As an undesirable consequence, hypothesis tests and confidence intervals based on asymptotic normality…

Statistics Theory · Mathematics 2023-03-23 Koulik Khamaru , Yash Deshpande , Tor Lattimore , Lester Mackey , Martin J. Wainwright

We consider the problem of imitation learning under misspecification: settings where the learner is fundamentally unable to replicate expert behavior everywhere. This is often true in practice due to differences in observation space and…

Machine Learning · Computer Science 2025-04-03 Nicolas Espinosa-Dice , Sanjiban Choudhury , Wen Sun , Gokul Swamy

The recent work by Dong & Yang (2023) showed for misspecified sparse linear bandits, one can obtain an $O\left(\epsilon\right)$-optimal policy using a polynomial number of samples when the sparsity is a constant, where $\epsilon$ is the…

Machine Learning · Computer Science 2024-07-19 Ally Yalei Du , Lin F. Yang , Ruosong Wang

We design and implement an adaptive experiment (a ``contextual bandit'') to learn a targeted treatment assignment policy, where the goal is to use a participant's survey responses to determine which charity to expose them to in a donation…

We provide a sound and consistent foundation for the use of \emph{nonrandom} exploration data in "contextual bandit" or "partially labeled" settings where only the value of a chosen action is learned. The primary challenge in a variety of…

Machine Learning · Computer Science 2010-06-15 Alex Strehl , John Langford , Sham Kakade , Lihong Li

Adaptive experiments are used extensively in online platforms, healthcare and biotechnology, and a variety of other settings. In many of these applications, the main goal is not to precisely estimate a treatment effect, but to demonstrate…

Statistics Theory · Mathematics 2026-03-10 Guido Imbens , Lorenzo Masoero , Alexander Rakhlin , Thomas S. Richardson , Suhas Vijaykumar

In reinforcement learning, it is typical to use the empirically observed transitions and rewards to estimate the value of a policy via either model-based or Q-fitting approaches. Although straightforward, these techniques in general yield…

Machine Learning · Computer Science 2020-07-28 Ilya Kostrikov , Ofir Nachum

Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present…

Machine Learning · Computer Science 2020-03-06 Arjun Sondhi , David Arbour , Drew Dimmery

This work presents a new approach, called MISFIT, for fitting generalized functional linear regression models with sparsely and irregularly sampled data. Current methods do not allow for consistent estimation unless one assumes that the…

Methodology · Statistics 2022-05-10 Justin Petrovich , Matthew Reimherr , Carrie Daymont

We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to…

Machine Learning · Computer Science 2019-01-16 Yifei Ma , Yu-Xiang Wang , Balakrishnan , Narayanaswamy

Contextual multi-armed bandits are a popular choice to model sequential decision-making. E.g., in a healthcare application we may perform various tests to asses a patient condition (exploration) and then decide on the best treatment to give…

Machine Learning · Computer Science 2025-04-08 Mirco Mutti , Jeongyeol Kwon , Shie Mannor , Aviv Tamar

Offline policy learning (OPL) leverages existing data collected a priori for policy optimization without any active exploration. Despite the prevalence and recent interest in this problem, its theoretical and algorithmic foundations in…

Machine Learning · Computer Science 2022-03-15 Thanh Nguyen-Tang , Sunil Gupta , A. Tuan Nguyen , Svetha Venkatesh

Solutions to address the periodic review inventory control problem with nonstationary random demand, lost sales, and stochastic vendor lead times typically involve making strong assumptions on the dynamics for either approximation or…

Machine Learning · Statistics 2023-10-26 Dean Foster , Randy Jia , Dhruv Madeka

We consider off-policy evaluation (OPE) in contextual bandits with finite action space. Inverse Propensity Score (IPS) weighting is a widely used method for OPE due to its unbiased, but it suffers from significant variance when the action…

Machine Learning · Computer Science 2025-10-15 Kushagra Chandak , Vincent Liu , Haanvid Lee

Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data…

Machine Learning · Statistics 2020-01-06 Yash Deshpande , Lester Mackey , Vasilis Syrgkanis , Matt Taddy

Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging…

Machine Learning · Computer Science 2021-03-01 Zhuangdi Zhu , Kaixiang Lin , Bo Dai , Jiayu Zhou

Neural density estimators have proven remarkably powerful in performing efficient simulation-based Bayesian inference in various research domains. In particular, the BayesFlow framework uses a two-step approach to enable amortized parameter…

Methodology · Statistics 2022-11-10 Marvin Schmitt , Paul-Christian Bürkner , Ullrich Köthe , Stefan T. Radev

Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as search engines, recommender systems, and etc. While the…

Machine Learning · Computer Science 2023-09-28 Xiaoying Zhang , Junpu Chen , Hongning Wang , Hong Xie , Yang Liu , John C. S. Lui , Hang Li