Wasserstein GAN Can Perform PCA

02/25/2019
by   Jaewoong Cho, et al.
0

Generative Adversarial Networks (GANs) have become a powerful framework to learn generative models that arise across a wide variety of domains. While there has been a recent surge in the development of numerous GAN architectures with distinct optimization metrics, we are still lacking in our understanding on how far away such GANs are from optimality. In this paper, we make progress on a theoretical understanding of the GANs under a simple linear-generator Gaussian-data setting where the optimal maximum-likelihood generator is known to perform Principal Component Analysis (PCA). We find that the original GAN by Goodfellow et. al. fails to recover the optimal PCA solution. On the other hand, we show that Wasserstein GAN can perform PCA, and hence it may serve as a basis for an optimal GAN architecture that yields the optimal generator for a wide range of data settings.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2017

Understanding GANs: the LQG Setting

Generative Adversarial Networks (GANs) have become a popular method to l...
research
05/06/2017

Face Super-Resolution Through Wasserstein GANs

Generative adversarial networks (GANs) have received a tremendous amount...
research
02/11/2020

Smoothness and Stability in GANs

Generative adversarial networks, or GANs, commonly display unstable beha...
research
09/13/2021

Inferential Wasserstein Generative Adversarial Networks

Generative Adversarial Networks (GANs) have been impactful on many probl...
research
09/19/2017

Summable Reparameterizations of Wasserstein Critics in the One-Dimensional Setting

Generative adversarial networks (GANs) are an exciting alternative to al...
research
02/10/2021

Conditional Versus Adversarial Euler-based Generators For Time Series

We introduce new generative models for time series based on Euler discre...
research
11/28/2017

Are GANs Created Equal? A Large-Scale Study

Generative adversarial networks (GAN) are a powerful subclass of generat...

Please sign up or login with your details

Forgot password? Click here to reset