DeepAI AI Chat
Log In Sign Up

On Unifying Deep Generative Models

by   Zhiting Hu, et al.
Petuum, Inc.
Carnegie Mellon University

Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as powerful frameworks for deep generative model learning, have largely been considered as two distinct paradigms and received extensive independent study respectively. This paper establishes formal connections between deep generative modeling approaches through a new formulation of GANs and VAEs. We show that GANs and VAEs are essentially minimizing KL divergences of respective posterior and inference distributions with opposite directions, extending the two learning phases of classic wake-sleep algorithm, respectively. The unified view provides a powerful tool to analyze a diverse set of existing model variants, and enables to exchange ideas across research lines in a principled way. For example, we transfer the importance weighting method in VAE literatures for improved GAN learning, and enhance VAEs with an adversarial mechanism for leveraging generated samples. Quantitative experiments show generality and effectiveness of the imported extensions.


page 1

page 2

page 3

page 4


Unifying Generative Models with GFlowNets

There are many frameworks for deep generative modeling, each often prese...

An Introduction to Deep Generative Modeling

Deep generative models (DGM) are neural networks with many hidden layers...

Approximate Query Processing using Deep Generative Models

Data is generated at an unprecedented rate surpassing our ability to ana...

Deep Knockoffs

This paper introduces a machine for sampling approximate model-X knockof...

KernelNet: A Data-Dependent Kernel Parameterization for Deep Generative Modeling

Learning with kernels is an often resorted tool in modern machine learni...

Refining Deep Generative Models via Wasserstein Gradient Flows

Deep generative modeling has seen impressive advances in recent years, t...

Feature Disentanglement in generating three-dimensional structure from two-dimensional slice with sliceGAN

Deep generative models are known to be able to model arbitrary probabili...