Deep learning, dark knowledge, and dark matter

Abstract

Particle colliders are the primary experimental instruments of high-energy physics. By cre-ating conditions that have not occurred naturally since the Big Bang, collider experiments aim to probe the most fundamental properties of matter and the universe. These costly experiments generate very large amounts of noisy data, creating important challenges and opportunities for machine learning. In this work we use deep learning to greatly improve the statistical power on three benchmark problems involving: (1) Higgs bosons; (2) su-persymmetric particles; and (3) Higgs boson decay modes. This approach increases the expected discovery significance over traditional shallow methods, by 50%, 2%, and 11% respectively. In addition, we explore the use of model compression to transfer information (dark knowledge) from deep networks to shallow networks.