.png){kind=icon}
返回
Cumulant GAN
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3161127.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this article, we propose a novel loss function for training generative adversarial networks (GANs) aiming toward deeper theoretical understanding as well as improved stability and performance for the underlying optimization problem. The new loss function is based on cumulant generating functions (CGFs) giving rise to Cumulant GAN. Relying on a recently derived variational formula, we show that the corresponding optimization problem is equivalent to Renyi divergence minimization, thus offering a (partially) unified perspective of GAN lasses: the Renyi family encompasses Kullback-Leibler divergence (KLD), reverse KLD, Hellinger distance, and chi(2)-divergence. Wasserstein GAN is also a member of cumulant GAN. In terms of stability, we rigorously prove the linear convergence of cumulant GAN to the Nash equilibrium for a linear discriminator, Gaussian distributions, and the standard gradient descent ascent algorithm. Finally, we experimentally demonstrate that image generation is more robust relative to Wasserstein GAN and it is substantially improved in terms of both inception score (IS) and Frichet inception distance (FID) when both weaker and stronger discriminators are considered.
Keyword:
Cumulant generating function (CGF)
generative adversarial networks (GANs)
image generation
Renyi divergence
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
.png){kind=icon}
Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏
查看更多内容