Renormalization in the neural network-quantum field theory correspondence - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Access content directly
Conference Poster Year : 2022

Renormalization in the neural network-quantum field theory correspondence

Abstract

A statistical ensemble of neural networks can be described in terms of a quantum field theory (NN-QFT correspondence). The infinite-width limit is mapped to a free field theory, while finite N corrections are mapped to interactions. After reviewing the correspondence, we will describe how to implement renormalization in this context and discuss preliminary numerical results for translation-invariant kernels. A major outcome is that changing the standard deviation of the neural network weight distribution corresponds to a renormalization flow in the space of networks.
Fichier principal
Vignette du fichier
erbin_lahoche_samary_2022_renormalization_in_the_neural_network-quantum_field_theory_correspondence.pdf (624.07 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

cea-04082366 , version 1 (26-04-2023)

Identifiers

Cite

Harold Erbin, Vincent Lahoche, Dine Ousmane Samary. Renormalization in the neural network-quantum field theory correspondence. NeurIPS 2022 - Machine Learning and the Physical Sciences - the 36th conference on Neural Information Processing Systems, Dec 2022, New Orléans, United States. , 2022. ⟨cea-04082366⟩
34 View
180 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More