Bidirectional Generative Modeling Using Adversarial Gradient Estimation
Machine Learning
2020-07-01 v3 Computer Vision and Pattern Recognition
Machine Learning
Abstract
This paper considers the general -divergence formulation of bidirectional generative modeling, which includes VAE and BiGAN as special cases. We present a new optimization method for this formulation, where the gradient is computed using an adversarially learned discriminator. In our framework, we show that different divergences induce similar algorithms in terms of gradient evaluation, except with different scaling. Therefore this paper gives a general recipe for a class of principled -divergence based generative modeling methods. Theoretical justifications and extensive empirical studies are provided to demonstrate the advantage of our approach over existing methods.
Cite
@article{arxiv.2002.09161,
title = {Bidirectional Generative Modeling Using Adversarial Gradient Estimation},
author = {Xinwei Shen and Tong Zhang and Kani Chen},
journal= {arXiv preprint arXiv:2002.09161},
year = {2020}
}