Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions

06/04/2021
by   Zeyuan Allen-Zhu, et al.
0

Generative adversarial networks (GANs) are among the most successful models for learning high-complexity, real-world distributions. However, in theory, due to the highly non-convex, non-concave landscape of the minmax training objective, GAN remains one of the least understood deep learning models. In this work, we formally study how GANs can efficiently learn certain hierarchically generated distributions that are close to the distribution of images in practice. We prove that when a distribution has a structure that we refer to as Forward Super-Resolution, then simply training generative adversarial networks using gradient descent ascent (GDA) can indeed learn this distribution efficiently, both in terms of sample and time complexities. We also provide concrete empirical evidence that not only our assumption "forward super-resolution" is very natural in practice, but also the underlying learning mechanisms that we study in this paper (to allow us efficiently train GAN via GDA in theory) simulates the actual learning process of GANs in practice on real-world problems.

READ FULL TEXT

page 4

page 5

page 9

page 11

page 12

page 16

page 20

research
04/28/2022

Generative Adversarial Networks for Image Super-Resolution: A Survey

Single image super-resolution (SISR) has played an important role in the...
research
01/18/2019

Generative Adversarial Classifier for Handwriting Characters Super-Resolution

Generative Adversarial Networks (GAN) receive great attentions recently ...
research
10/04/2020

Spatial Frequency Bias in Convolutional Generative Adversarial Networks

As the success of Generative Adversarial Networks (GANs) on natural imag...
research
05/20/2020

Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network

Generative adversarial networks (GANs) have been recently adopted for su...
research
05/29/2017

Learning to Generate Chairs with Generative Adversarial Nets

Generative adversarial networks (GANs) has gained tremendous popularity ...
research
02/08/2021

Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack

Ever since Machine Learning as a Service (MLaaS) emerges as a viable bus...
research
10/28/2019

Decentralized Parallel Algorithm for Training Generative Adversarial Nets

Generative Adversarial Networks (GANs) are powerful class of generative ...

Please sign up or login with your details

Forgot password? Click here to reset