Timezone: »

 
Poster
Efficient Policy Learning from Surrogate-Loss Classification Reductions
Andrew Bennett · Nathan Kallus

Wed Jul 15 08:00 AM -- 08:45 AM & Wed Jul 15 07:00 PM -- 07:45 PM (PDT) @ Virtual #None

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 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 semi-parametric 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.

Author Information

Andrew Bennett (Cornell University)
Nathan Kallus (Cornell University)

More from the Same Authors