Machine Learning's Dropout Training is Distributionally Robust Optimal

no code implementations • 13 Sep 2020 • Jose Blanchet, Yang Kang, Jose Luis Montiel Olea, Viet Anh Nguyen, Xuhui Zhang

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 covariates using a multiplicative nonparametric errors-in-variables model.

Competing Models

no code implementations • 8 Jul 2019 • Jose Luis Montiel Olea, Pietro Ortoleva, Mallesh M. Pai, Andrea Prat

Different agents need to make a prediction.

Model Selection Small Data Image Classification