Neural Networks and Quantum Field Theory

Jim Halverson (Northeastern University)

04-Sep-2020, 13:30-14:30 (4 years ago)

Abstract: We propose a theoretical understanding of neural networks in terms of Wilsonian effective field theory. The correspondence relies on the fact that many asymptotic neural networks are drawn from Gaussian processes, the analog of non-interacting field theories. Moving away from the asymptotic limit yields a non-Gaussian process and corresponds to turning on particle interactions, allowing for the computation of correlation functions of neural network outputs with Feynman diagrams. Minimal non-Gaussian process likelihoods are determined by the most relevant non-Gaussian terms, according to the flow in their coefficients induced by the Wilsonian renormalization group. This yields a direct connection between overparameterization and simplicity of neural network likelihoods. Whether the coefficients are constants or functions may be understood in terms of GP limit symmetries, as expected from 't Hooft's technical naturalness. General theoretical calculations are matched to neural network experiments in the simplest class of models allowing the correspondence. Our formalism is valid for any of the many architectures that becomes a GP in an asymptotic limit, a property preserved under certain types of training.

cosmology and nongalactic astrophysicsother condensed matterquantum gasesstrongly correlated electronssuperconductivitymachine learningneural and evolutionary computinggeneral relativity and quantum cosmologyHEP - theory

Audience: researchers in the topic


Carnegie Mellon theoretical physics

Organizer: Riccardo Penco*
*contact for this listing

Export talk to