BriefGPT.xyz
Oct, 2019
理解变分互信息估计器的局限性
Understanding the Limitations of Variational Mutual Information Estimators
HTML
PDF
Jiaming Song, Stefano Ermon
TL;DR
论文提出并实现了一种新的基于神经网络的相互信息估计方法,该方法能够有效地减少方差并针对基准测试任务展现出更好的偏差-方差权衡性能。
Abstract
Variational approaches based on
neural networks
are showing promise for estimating
mutual information
(MI) between high dimensional variables. However, they can be difficult to use in practice due to poorly under
→