Efficient Policy Learning from Surrogate-Loss Classification Reductions

arXiv2002.05153MaRDI QIDQ6334699

Author name not available (Why is that?)

Publication date: 12 February 2020

Abstract: Recent work on policy learning from observational data has highlighted the importance of efficient policy evaluation and has proposed reductions to weighted (cost-sensitive) classification. But, efficient policy evaluation need not yield efficient estimation of policy parameters. We consider the estimation problem given by a weighted surrogate-loss classification reduction of policy learning with any score function, either direct, inverse-propensity weighted, or doubly robust. We show that, under a correct specification assumption, the weighted classification formulation need not be efficient for policy parameters. We draw a contrast to actual (possibly weighted) binary classification, where correct specification implies a parametric model, while for policy learning it only implies a semiparametric model. In light of this, we instead propose an estimation approach based on generalized method of moments, which is efficient for the policy parameters. We propose a particular method based on recent developments on solving moment problems using neural networks and demonstrate the efficiency and regret benefits of this method empirically.

Has companion code repository: https://github.com/CausalML/ESPRM

This page was built for publication: Efficient Policy Learning from Surrogate-Loss Classification Reductions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6334699)