33 citations · 69 across the 6 of their papers we have counts for
6 papers
Machine Learning's Dropout Training is Distributionally Robust Optimal
Jose Blanchet, Yang Kang, Jose Luis Montiel Olea +2
This paper shows that dropout training in Generalized Linear Models is the minimax solution of a two-player, zero-sum game where an adversarial nature corrupts a statistician's cov…
A Distributionally Robust Boosting Algorithm
Jose Blanchet, Yang Kang, Fan Zhang +1
Distributionally Robust Optimization (DRO) has been shown to provide a flexible framework for decision making under uncertainty and statistical estimation. For example, recent work…
Doubly Robust Data-Driven Distributionally Robust Optimization
Jose Blanchet, Yang Kang, Fan Zhang +2
Data-driven Distributionally Robust Optimization (DD-DRO) via optimal transport has been shown to encompass a wide range of popular machine learning algorithms. The distributional…
Distributionally Robust Groupwise Regularization Estimator
Jose Blanchet, Yang Kang
Regularized estimators in the context of group variables have been applied successfully in model and feature selection in order to preserve interpretability. We formulate a Distrib…
Data-driven Optimal Cost Selection for Distributionally Robust Optimization
Jose Blanchet, Yang Kang, Fan Zhang +1
Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and reg…
Sample Out-Of-Sample Inference Based on Wasserstein Distance
Jose Blanchet, Yang Kang
We present a novel inference approach that we call Sample Out-of-Sample (or SOS) inference. The approach can be used widely, ranging from semi-supervised learning to stress testing…