hep-phMay 28, 2026

Generative Models and Statistical Validation

Authors: Sascha DiefenbacherSofia Palacios SchweitzerGregor Kasieczka

Organizations: Institut für Theoretische Physik, Universität Heidelberg, Germany · Physics Division, Lawrence Berkeley National Laboratory, Berkeley, USA · NHETC, Department of Physics & Astronomy, Rutgers University, Piscataway, NJ, USA · Institut für Experimentalphysik, Universität Hamburg, Germany

Abstract

Generative machine learning has become an essential tool in theoretical and experimental physics, especially in the context of fast surrogates and density estimators. In this work, we first introduce the underlying framework of modern generative networks and then discuss challenges in quantifying their accuracy, precision, and statistical power.

Explore similar work

CardsList
  1. Forecasting Generative Amplification

    Sep 9, 2025Henning Bahl, Sascha Diefenbacher, Nina Elmer +2High Energy PhysicsGenerative Models