Machine Learning Opportunities for the Next Generation of Particle Physics

At the CERN Large Hadron Collider, protons collide 40 million times per second at the highest energies achievable in the lab, probing the microscopic nature of subatomic particles on the smallest length scales. These proton-proton collisions give rise to thousands of particles per collision, whose energy deposits and hits are measured by massive detectors and read out as hundreds of millions of data channels. By comparing this data to those predicted by theory through simulation, we can test the validity of our theory and search for the existence of new particles, like dark matter, or interactions, like the elusive Higgs boson self-interaction. This avalanche of data will continue to grow in the next generation of experiments, posing tremendous challenges. Machine learning (ML) methods are increasingly essential to analyze this data while overcoming these challenges. In this talk, I will cover several opportunities to apply ML to reconstruct particles from detector measurements, simulate collisions, filter collisions in real time, and perhaps even discover new physical laws or symmetries.

Bio: Javier Duarte is an Associate Professor of Physics at UC San Diego and a member of the CMS experiment at the CERN Large Hadron Collider. He leads a research group developing new artificial intelligence (AI) techniques for high-energy particle collisions to better measure the properties and interactions of elementary particles, like the Higgs boson, and search for new physics. Before joining UC San Diego, he was a Lederman postdoctoral fellow at Fermilab and received his Ph.D. in Physics at Caltech and his B.S. in Physics and Mathematics at MIT. Prof. Duarte has received the APS Henry Primakoff Award for Early-Career Particle Physics, Sloan Research Fellowship, RCSA Cottrell Scholar Award, DOE Early Career Award, and is a co-PI of the NSF HDR Institute for Accelerated AI Algorithms for Data-Driven Discovery (A3D3).