A Spin Glass Model for the Loss Surfaces of Generative Adversarial Networks.
J Stat Phys
; 186(2): 29, 2022.
Article
en En
| MEDLINE
| ID: mdl-35125517
ABSTRACT
We present a novel mathematical model that seeks to capture the key design feature of generative adversarial networks (GANs). Our model consists of two interacting spin glasses, and we conduct an extensive theoretical analysis of the complexity of the model's critical points using techniques from Random Matrix Theory. The result is insights into the loss surfaces of large GANs that build upon prior insights for simpler networks, but also reveal new structure unique to this setting which explains the greater difficulty of training GANs.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Idioma:
En
Revista:
J Stat Phys
Año:
2022
Tipo del documento:
Article