Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2021

Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit

Fichier principal
Vignette du fichier
project1_arxiv_v2.pdf (1.52 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03388815 , version 1 (20-10-2021)
hal-03388815 , version 2 (28-10-2021)
hal-03388815 , version 3 (06-12-2021)

Identifiers

Cite

Karl Hajjar, Lénaïc Chizat, Christophe Giraud. Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit. 2021. ⟨hal-03388815v3⟩
222 View
108 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More