Nguyen, V. A., Zhang, F., Blanchet, J., Delage, E., & Ye, Y. (2020). Distributionally Robust Local Non-parametric Conditional Estimation. ArXiv. /abs/2010.05373

View Publication

Abstract

Conditional estimation given specific covariate values (ie, local conditional estimation or functional estimation) is ubiquitously useful with applications in engineering, social and natural sciences. Existing data-driven non-parametric estimators mostly focus on structured homogeneous data (eg, weakly independently and stationary data), thus they are sensitive to adversarial noise and may perform poorly under a low sample size. To alleviate these issues, we propose a new distributionally robust estimator that generates non-parametric local estimates by minimizing the worst-case conditional expected loss over all adversarial distributions in a Wasserstein ambiguity set. We show that despite being generally intractable, the local estimator can be efficiently found via convex optimization under broadly applicable settings, and it is robust to the corruption and heterogeneity of the data. Various experiments show the competitive performance of this new class of estimator.

Authors
Viet Anh Nguyen, Fan Zhang, Jose Blanchet, Erick Delage, Yinyu Ye
Publication date
2020
Journal
Advances in Neural Information Processing Systems
Volume
33
Pages
15232-15242