Variational Inference: A Unified Framework of Generative Models and Some Revelations

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.

6 pages, 4 figures, fix a bug, fix (19), E(z)-->E(x), fix (2), fix (7), add code link

References in corpus (3)

• Adversarial Feature Learning
• Adversarially Learned Inference
• On Unifying Deep Generative Models

Cited by in corpus (2)

• Amortized Variational Inference: A Systematic Review
• A Mathematical Framework for Learning Probability Distributions