"Best-of-Many-Samples" Distribution Matching
arXiv:1909.12598
Abstract
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.
References in corpus (15)
- Auto-Encoding Variational Bayes
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Adversarial Feature Learning
- Adversarially Learned Inference
- InfoVAE: Information Maximizing Variational Autoencoders
- Mode Regularized Generative Adversarial Networks
- Banach Wasserstein GAN
- Amortized Inference Regularization
- Distribution Matching in Variational Inference
- Cramer-Wold AutoEncoder
- Can VAEs Generate Novel Examples?