DeepAI
Log In Sign Up

A spin-glass model for the loss surfaces of generative adversarial networks

01/07/2021
by   Nicholas P. Baskerville, et al.
7

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.

READ FULL TEXT

page 11

page 12

page 20

page 22

06/29/2018

Convergence Problems with Generative Adversarial Networks (GANs)

Generative adversarial networks (GANs) are a novel approach to generativ...
11/27/2016

Handwriting Profiling using Generative Adversarial Networks

Handwriting is a skill learned by humans from a very early age. The abil...
02/22/2022

Generating Synthetic Mobility Networks with Generative Adversarial Networks

The increasingly crucial role of human displacements in complex societal...
06/03/2020

Multiple Generative Adversarial Networks Analysis for Predicting Photographers' Retouching

Anyone can take a photo, but not everybody has the ability to retouch th...
11/17/2017

High-Resolution Deep Convolutional Generative Adversarial Networks

Generative Adversarial Networks (GANs) convergence in a high-resolution ...
01/17/2017

Towards Principled Methods for Training Generative Adversarial Networks

The goal of this paper is not to introduce a single algorithm or method,...