@online{Bhattacharyya_arXiv1909.12598,
TITLE = {"Best-of-Many-Samples" Distribution Matching},
AUTHOR = {Bhattacharyya, Apratim and Fritz, Mario and Schiele, Bernt},
LANGUAGE = {eng},
URL = {http://arxiv.org/abs/1909.12598},
EPRINT = {1909.12598},
EPRINTTYPE = {arXiv},
YEAR = {2019},
ABSTRACT = {Generative Adversarial Networks (GANs) can achieve state-of-the-art sample<br>quality in generative modelling tasks but suffer from the mode collapse<br>problem. Variational Autoencoders (VAE) on the other hand explicitly maximize a<br>reconstruction-based data log-likelihood forcing it to cover all modes, but<br>suffer from poorer sample quality. Recent works have proposed hybrid VAE-GAN<br>frameworks which integrate a GAN-based synthetic likelihood to the VAE<br>objective to address both the mode collapse and sample quality issues, with<br>limited success. This is because the VAE objective forces a trade-off between<br>the data log-likelihood and divergence to the latent prior. The synthetic<br>likelihood ratio term also shows instability during training. We propose a<br>novel objective with a "Best-of-Many-Samples" reconstruction cost and a stable<br>direct estimate of the synthetic likelihood. This enables our hybrid VAE-GAN<br>framework to achieve high data log-likelihood and low divergence to the latent<br>prior at the same time and shows significant improvement over both hybrid<br>VAE-GANS and plain GANs in mode coverage and quality.<br>},
}