Blanchet J, Kang Y, Murthy K. Robust Wasserstein profile inference and applications to machine learning. Journal of Applied Probability. 2019;56(3):830-857. doi:10.1017/jpr.2019.49
Abstract
We show that several machine learning estimators, including square-root least absolute shrinkage and selection and regularized logistic regression, can be represented as solutions to distributionally robust optimization problems. The associated uncertainty regions are based on suitably defined Wasserstein distances. Hence, our representations allow us to view regularization as a result of introducing an artificial adversary that perturbs the empirical distribution to account for out-of-sample effects in loss estimation. In addition, we introduce RWPI (robust Wasserstein profile inference), a novel inference methodology which extends the use of methods inspired by empirical likelihood to the setting of optimal transport costs (of which Wasserstein distances are a particular case). We use RWPI to show how to optimally select the size of uncertainty regions, and as a consequence we are able to choose regularization …
Authors: Jose Blanchet, Yang Kang, Karthyek Murthy
Publication date: 2019/9
Journal: Journal of Applied Probability
Volume: 56
Issue: 3
Pages: 830-857
Publisher: Cambridge University Press
