Intern
RTG 2994 Particle physics at colliders in the LHC precision era

RTG Seminar by Prof. Dr. Zohar Ringel

06.06.2025

The next seminar for our Research Training Group will be online on June 12 at 2:15 p.m. The speaker is Prof. Dr. Zohar Ringel.

Prof. Dr. Zohar Ringel, Hebrew University of Jerusalem
Title: A unified field theory approach to feature learning and generalization
12. June 2025 - Online - 2:15 p.m.

One of the main merits of field theory is its role as a common language for reasoning about physical systems. In this talk, I'll portray how it may play a similar role in deep learning. In the first part, we'll set up a general field theory formulation of Bayesian Neural Networks or Langevin-trained DNNs at equilibrium. The aim would be to reproduce various known results within this unifying perspective using standard field theory methods. We'll start by deriving the DNN to Gaussian-Process correspondence at infinite width and obtain the dataset-averaged Gaussian Process action. We would then discuss the actions associated with finite-width DNNs and how two types of mean-field approximations on the interaction/non-linear terms in those actions can explain some of the mysteries of deep learning: DNNs' ability to generalize well despite having infinite expressibility and DNNs' ability to learn functions with better sample complexity scaling than their corresponding infinite-width/GP limit.