Reparameterized Sampling for Generative Adversarial Networks

07/01/2021
by   Yifei Wang, et al.
0

Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs). However, in practice, they typically have poor sample efficiency because of the independent proposal sampling from the generator. In this work, we propose REP-GAN, a novel sampling method that allows general dependent proposals by REParameterizing the Markov chains into the latent space of the generator. Theoretically, we show that our reparameterized proposal admits a closed-form Metropolis-Hastings acceptance ratio. Empirically, extensive experiments on synthetic and real datasets demonstrate that our REP-GAN largely improves the sample efficiency and obtains better sample quality simultaneously.

READ FULL TEXT

page 14

page 17

09/28/2020

EvolGAN: Evolutionary Generative Adversarial Networks

We propose to use a quality estimator and evolutionary methods to search...
01/30/2021

Time Series (re)sampling using Generative Adversarial Networks

We propose a novel bootstrap procedure for dependent data based on Gener...
07/28/2020

Improving Generative Adversarial Networks with Local Coordinate Coding

Generative adversarial networks (GANs) have shown remarkable success in ...
06/13/2022

Exploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling

Despite the extensive studies on Generative Adversarial Networks (GANs),...
11/21/2018

Self-Adversarially Learned Bayesian Sampling

Scalable Bayesian sampling is playing an important role in modern machin...
11/02/2020

Sampling-Decomposable Generative Adversarial Recommender

Recommendation techniques are important approaches for alleviating infor...
11/23/2019

Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference

Inferring the latent variable generating a given test sample is a challe...