Generative Adversarial Nets from a Density Ratio Estimation Perspective
Machine Learning
2016-11-10 v2
Abstract
Generative adversarial networks (GANs) are successful deep generative models. GANs are based on a two-player minimax game. However, the objective function derived in the original motivation is changed to obtain stronger gradients when learning the generator. We propose a novel algorithm that repeats the density ratio estimation and f-divergence minimization. Our algorithm offers a new perspective toward the understanding of GANs and is able to make use of multiple viewpoints obtained in the research of density ratio estimation, e.g. what divergence is stable and relative density ratio is useful.
Cite
@article{arxiv.1610.02920,
title = {Generative Adversarial Nets from a Density Ratio Estimation Perspective},
author = {Masatoshi Uehara and Issei Sato and Masahiro Suzuki and Kotaro Nakayama and Yutaka Matsuo},
journal= {arXiv preprint arXiv:1610.02920},
year = {2016}
}
Comments
Add contents especially theoretical things for ICLR 2017