Minimax Estimation of Neural Net Distance
Minimax Estimation of Neural Net Distance
复制标题
神经网络距离的极小极大估计
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Yingbin Liang
中科院分区：
文献类型：
--
作者：
Kaiyi Ji;Yingbin Liang
为训练生成对抗网络（GAN）提出的一类重要距离指标是积分概率度量（IPM），其中神经净距离通过两个神经网络捕获实用的GAN训练。本文根据从分布中得出的样本研究了神经净距离的最小估计问题。我们在神经净距离的估计误差上开发了第一个已知的最小值下限，并且比现有的界限比在经验神经净距离的估计器误差上更紧密。我们的上限和上限不仅在样本量的顺序上，而且在神经网络的参数矩阵的规范方面匹配，这证明了经验神经网距实践。
An important class of distance metrics proposed for training generative adversarial networks (GANs) is the integral probability metric (IPM), in which the neural net distance captures the practical GAN training via two neural networks. This paper investigates the minimax estimation problem of the neural net distance based on samples drawn from the distributions. We develop the first known minimax lower bound on the estimation error of the neural net distance, and an upper bound tighter than an existing bound on the estimator error for the empirical neural net distance. Our lower and upper bounds match not only in the order of the sample size but also in terms of the norm of the parameter matrices of neural networks, which justifies the empirical neural net distance as a good approximation of the true neural net distance for training GANs in practice.
通过网络进行几何结构的非参数检测
影响因子：
5.4
作者：
Zou, Shaofeng;Liang, Yingbin;Poor, H. Vincent
通讯作者：
Poor, H. Vincent