Kernel-based off-policy estimation without overlap: Instance optimality
beyond semiparametric efficiency

Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency

16 January 2023

Martin J. Wainwright

Peter L. Bartlett

Papers citing "Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency"

10 / 10 papers shown

Title
A decorrelation method for general regression adjustment in randomized experiments Fangzhou Su Wenlong Mou Peng Ding Martin J. Wainwright 19 1 0 16 Nov 2023
Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization Sanath Kumar Krishnamurthy Ruohan Zhan Susan Athey Emma Brunskill 30 6 0 05 Jul 2023
$K$ -Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control Michael Giegrich Roel Oomen C. Reisinger OffRL 17 2 0 07 Jun 2023
Off-policy evaluation beyond overlap: partial identification through smoothness Samir Khan Martin Saveski J. Ugander OffRL 22 5 0 19 May 2023
Augmented balancing weights as linear regression David Bruns-Smith O. Dukes Avi Feller Elizabeth L. Ogburn 27 10 0 27 Apr 2023
Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift Kaizheng Wang 19 10 0 20 Feb 2023
A New Central Limit Theorem for the Augmented IPW Estimator: Variance Inflation, Cross-Fit Covariance and Beyond Kuanhao Jiang Rajarshi Mukherjee Subhabrata Sen Pragya Sur 23 11 0 20 May 2022
Off-Policy Evaluation Using Information Borrowing and Context-Based Switching Sutanoy Dasgupta Yabo Niu Kishan Panaganti D. Kalathil D. Pati Bani Mallick OffRL 19 0 0 18 Dec 2021
Kernel Ridge Riesz Representers: Generalization, Mis-specification, and the Counterfactual Effective Dimension Rahul Singh CML 15 8 0 22 Feb 2021
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes Nathan Kallus Masatoshi Uehara OffRL 33 180 0 22 Aug 2019