English

Distributionally Robust Counterfactual Risk Minimization

Machine Learning 2019-12-17 v2 Machine Learning

Abstract

This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem. Tapping into a rich existing literature, we show that DRO is a principled tool for counterfactual decision making. We also show that well-established solutions to the CRM problem like sample variance penalization schemes are special instances of a more general DRO problem. In this unifying framework, a variety of distributionally robust counterfactual risk estimators can be constructed using various probability distances and divergences as uncertainty measures. We propose the use of Kullback-Leibler divergence as an alternative way to model uncertainty in CRM and derive a new robust counterfactual objective. In our experiments, we show that this approach outperforms the state-of-the-art on four benchmark datasets, validating the relevance of using other uncertainty measures in practical applications.

Keywords

Cite

@article{arxiv.1906.06211,
  title  = {Distributionally Robust Counterfactual Risk Minimization},
  author = {Louis Faury and Ugo Tanielian and Flavian Vasile and Elena Smirnova and Elvis Dohmatob},
  journal= {arXiv preprint arXiv:1906.06211},
  year   = {2019}
}

Comments

Accepted at AAAI20

R2 v1 2026-06-23T09:53:53.313Z