Data Science Lecture: Lorentz-Equivariant Machine Learning for Particle Physics

by Alexander Bogatskii (Flatiron Institute)

Tuesday 4 Apr 2023, 09:00 → 11:00 Europe/Berlin

Rm 125 (Bdg. 68)

As usage of neural networks continues to grow in the field of particle physics, and as research in computer vision has demonstrated the usefulness of exploiting symmetries in data via network design, there is renewed interest in embedding the symmetries relevant to physics problems in neural networks which analyze them, as a means of applying physically-meaningful network constraints. I will briefly review common approaches to equivariant machine learning, introduce our older work on LGN (“Lorentz Group Network”), and present the newer architecture “PELICAN”, which now provides state-of-the-art performance when applied to jet tagging and momentum reconstruction, and does so with much lower model complexity than other ML approaches.

 

This event is part of a series of lectures and tutorials on data science topics hosted by the Platform for Challenges in Data Science in the excellence cluster "Quantum Universe" between DESY and Universität Hamburg. It is intended specifically for the PhD students in the cluster but younger and more senior members are of course also welcome.

PELICAN long.pdf

Recording dsl_sose23_1.mp4