Composite Functional Gradient Learning of Generative Adversarial Models

登录免费注册

资源分类

论文
算法
数据集
经验分享
技术动态
行业动态

论文
学习
研究领域

算法
学习
研究领域

数据集
自动驾驶
图片

经验分享
学习
研究领域

技术动态
计算机视觉
自然语言处理

行业动态
教育
语音识别

》资源》论文》Composite Functional Gradient Learning of Generative Adversarial Models

Composite Functional Gradient Learning of Generative Adversarial Models

2020-03-19 |

58 |

36 |

Composite Functional Gradient Learning of Generative Adversarial Models
论文

Abstract

This paper first presents a theory for generative adversarial methods that does not rely on the traditional minimax formulation. It shows that with a strong discriminator, a good generator can be learned so that the KL divergence between the distributions of real data and generated data improves after each functional gradient step until it converges to zero. Based on the theory, we propose a new stable generative adversarial method. A theoretical insight into the original GAN from this new viewpoint is also provided. The experiments on image generation show the effectiveness of our new method.

上一篇：High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach

下一篇：QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

用户评价