Bayesian Nonparametrics Meets Data-Driven Robust Optimization

Training machine learning and statistical models often involves optimizing a data-driven risk criterion. The risk is usually computed with respect to the empirical data distribution, but this may result in poor and unstable out-of-sample performance due to distributional uncertainty. In the spirit of distributionally robust optimization, we propose a novel robust criterion by combining insights from Bayesian nonparametric (i.e., Dirichlet Process) theory and recent decision-theoretic models of smooth ambiguity-averse preferences. First, we highlight novel connections with standard regularized empirical risk …

bayesian criterion cs.lg data data-driven distribution machine machine learning novel optimization performance risk robust sample statistical stat.ml training uncertainty