Bayesian Nonparametrics Meets Data-Driven Robust Optimization. (arXiv:2401.15771v2 [stat.ML] UPDATED)

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 …

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