Distributionally Robust Counterfactual Risk Minimization - Archive ouverte HAL Access content directly
Conference Papers Year :

Distributionally Robust Counterfactual Risk Minimization

Louis Faury
  • Function : Author
Ugo Tanielian
  • Function : Author
Flavian Vasile
  • Function : Author
  • PersonId : 1053681
Elena Smirnova
  • Function : Author
  • PersonId : 1065105
Elvis Dohmatob
  • Function : Author
  • PersonId : 956319

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.

Dates and versions

hal-02482843 , version 1 (18-02-2020)

Identifiers

Cite

Louis Faury, Ugo Tanielian, Flavian Vasile, Elena Smirnova, Elvis Dohmatob. Distributionally Robust Counterfactual Risk Minimization. AAAI20, Feb 2020, New York, United States. ⟨hal-02482843⟩

Collections

INSMI
53 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More