Variational Inference: A Unified Framework of Generative Models and Some Revelations
Machine Learning
2018-07-23 v4 Machine Learning
Abstract
We reinterpreting the variational inference in a new perspective. Via this way, we can easily prove that EM algorithm, VAE, GAN, AAE, ALI(BiGAN) are all special cases of variational inference. The proof also reveals the loss of standard GAN is incomplete and it explains why we need to train GAN cautiously. From that, we find out a regularization term to improve stability of GAN training.
Keywords
Cite
@article{arxiv.1807.05936,
title = {Variational Inference: A Unified Framework of Generative Models and Some Revelations},
author = {Jianlin Su},
journal= {arXiv preprint arXiv:1807.05936},
year = {2018}
}
Comments
6 pages, 4 figures, fix a bug, fix (19), E(z)-->E(x), fix (2), fix (7), add code link