Stabilizing Training of Generative Adversarial Networks through Regularization

05/25/2017
by   Kevin Roth, et al.
0

Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters. This fragility is in part due to a dimensional mismatch or non-overlapping support between the model distribution and the data distribution, causing their density ratio and the associated f-divergence to be undefined. We overcome this fundamental limitation and propose a new regularization approach with low computational cost that yields a stable GAN training procedure. We demonstrate the effectiveness of this regularizer across several architectures trained on common benchmark image generation tasks. Our regularization turns GAN models into reliable building blocks for deep learning.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 8

page 14

page 15

page 16

page 17

page 18

06/25/2019

AGAN: Towards Automated Design of Generative Adversarial Networks

Recent progress in Generative Adversarial Networks (GANs) has shown prom...
05/29/2019

KG-GAN: Knowledge-Guided Generative Adversarial Networks

Generative adversarial networks (GANs) learn to mimic training data that...
10/10/2016

Generative Adversarial Nets from a Density Ratio Estimation Perspective

Generative adversarial networks (GANs) are successful deep generative mo...
08/15/2019

Cosmological N-body simulations: a challenge for scalable generative models

Deep generative models, such as Generative Adversarial Networks (GANs) o...
07/12/2018

The GAN Landscape: Losses, Architectures, Regularization, and Normalization

Generative Adversarial Networks (GANs) are a class of deep generative mo...
08/19/2019

PolyGAN: High-Order Polynomial Generators

Generative Adversarial Networks (GANs) have become the gold standard whe...
06/04/2019

Encoding Invariances in Deep Generative Models

Reliable training of generative adversarial networks (GANs) typically re...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.