"Best-of-Many-Samples" Distribution Matching

09/27/2019
by   Apratim Bhattacharyya, et al.
17

Generative Adversarial Networks (GANs) can achieve state-of-the-art sample quality in generative modelling tasks but suffer from the mode collapse problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a reconstruction-based data log-likelihood forcing it to cover all modes, but suffer from poorer sample quality. Recent works have proposed hybrid VAE-GAN frameworks which integrate a GAN-based synthetic likelihood to the VAE objective to address both the mode collapse and sample quality issues, with limited success. This is because the VAE objective forces a trade-off between the data log-likelihood and divergence to the latent prior. The synthetic likelihood ratio term also shows instability during training. We propose a novel objective with a "Best-of-Many-Samples" reconstruction cost and a stable direct estimate of the synthetic likelihood. This enables our hybrid VAE-GAN framework to achieve high data log-likelihood and low divergence to the latent prior at the same time and shows significant improvement over both hybrid VAE-GANS and plain GANs in mode coverage and quality.

READ FULL TEXT

page 6

page 8

page 13

page 14

10/09/2019

Prescribed Generative Adversarial Networks

Generative adversarial networks (GANs) are a powerful approach to unsupe...
01/28/2019

Out-of-Sample Testing for GANs

We propose a new method to evaluate GANs, namely EvalGAN. EvalGAN relies...
11/30/2021

Exponentially Tilted Gaussian Prior for Variational Autoencoder

An important propertyfor deep neural networks to possess is the ability ...
02/19/2018

Distribution Matching in Variational Inference

The difficulties in matching the latent posterior to the prior, balancin...
05/11/2022

A Unified f-divergence Framework Generalizing VAE and GAN

Developing deep generative models that flexibly incorporate diverse meas...
02/03/2019

Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds

Since the introduction of Generative Adversarial Networks (GANs) and Var...
11/04/2019

Improved BiGAN training with marginal likelihood equalization

We propose a novel training procedure for improving the performance of g...

Code Repositories

GAN-Leaks

Official implementation of "GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models" (CCS 2020)


view repo