Cargando…

Bayesian interpolation with deep linear networks

Characterizing how neural network depth, width, and dataset size jointly impact model quality is a central problem in deep learning theory. We give here a complete solution in the special case of linear networks with output dimension one trained using zero noise Bayesian inference with Gaussian weig...

Descripción completa

Detalles Bibliográficos
Autores principales: Hanin, Boris, Zlokapa, Alexander
Formato: Online Artículo Texto
Lenguaje:English
Publicado: National Academy of Sciences 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10266010/
https://www.ncbi.nlm.nih.gov/pubmed/37252994
http://dx.doi.org/10.1073/pnas.2301345120