Semi-Implicit Generative Model
Machine Learning
2019-07-30 v2 Machine Learning
Abstract
To combine explicit and implicit generative models, we introduce semi-implicit generator (SIG) as a flexible hierarchical model that can be trained in the maximum likelihood framework. Both theoretically and experimentally, we demonstrate that SIG can generate high quality samples especially when dealing with multi-modality. By introducing SIG as an unbiased regularizer to the generative adversarial network (GAN), we show the interplay between maximum likelihood and adversarial learning can stabilize the adversarial training, resist the notorious mode collapsing problem of GANs, and improve the diversity of generated random samples.
Cite
@article{arxiv.1905.12659,
title = {Semi-Implicit Generative Model},
author = {Mingzhang Yin and Mingyuan Zhou},
journal= {arXiv preprint arXiv:1905.12659},
year = {2019}
}
Comments
Third workshop on Bayesian Deep Learning (NeurIPS 2018), Montreal, Canada