Dissecting adaptive methods in GANs

10/09/2022
by   Samy Jelassi, et al.
0

Adaptive methods are a crucial component widely used for training generative adversarial networks (GANs). While there has been some work to pinpoint the "marginal value of adaptive methods" in standard tasks, it remains unclear why they are still critical for GAN training. In this paper, we formally study how adaptive methods help train GANs; inspired by the grafting method proposed in arXiv:2002.11803 [cs.LG], we separate the magnitude and direction components of the Adam updates, and graft them to the direction and magnitude of SGDA updates respectively. By considering an update rule with the magnitude of the Adam update and the normalized direction of SGD, we empirically show that the adaptive magnitude of Adam is key for GAN training. This motivates us to have a closer look at the class of normalized stochastic gradient descent ascent (nSGDA) methods in the context of GAN training. We propose a synthetic theoretical framework to compare the performance of nSGDA and SGDA for GAN training with neural networks. We prove that in that setting, GANs trained with nSGDA recover all the modes of the true distribution, whereas the same networks trained with SGDA (and any learning rate configuration) suffer from mode collapse. The critical insight in our analysis is that normalizing the gradients forces the discriminator and generator to be updated at the same pace. We also experimentally show that for several datasets, Adam's performance can be recovered with nSGDA methods.

READ FULL TEXT

page 16

page 17

page 19

page 20

page 21

page 22

research
10/15/2019

SGD Learns One-Layer Networks in WGANs

Generative adversarial networks (GANs) are a widely used framework for l...
research
06/26/2017

GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

Generative Adversarial Networks (GANs) excel at creating realistic image...
research
02/13/2018

First Order Generative Adversarial Networks

GANs excel at learning high dimensional distributions, but they can upda...
research
08/28/2020

Adaptive WGAN with loss change rate balancing

Optimizing the discriminator in Generative Adversarial Networks (GANs) t...
research
02/06/2018

Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN

We relate the minimax game of generative adversarial networks (GANs) to ...
research
10/24/2019

Seeing What a GAN Cannot Generate

Despite the success of Generative Adversarial Networks (GANs), mode coll...
research
08/04/2018

Global Convergence to the Equilibrium of GANs using Variational Inequalities

In optimization, the negative gradient of a function denotes the directi...

Please sign up or login with your details

Forgot password? Click here to reset