Deep Gaussian networks for function approximation on data defined manifolds

Deep Gaussian networks for function approximation on data defined manifolds
复制标题

用于数据定义流形上函数逼近的深度高斯网络

DOI:
--
复制
发表时间:
2019
期刊:
arXiv.org
影响因子:
--
通讯作者:
H. Mhaskar
H. Mhaskar
中科院分区:
--
文献类型:
--
作者:
H. Mhaskar

文献摘要

参考文献

被引文献

相似文献

在许多关于深度网络函数逼近的文献中,函数被假定定义在某个已知的区域上,例如立方体或球体。在实际应用中,这些区域上的数据可能不是稠密的,因此,近似理论结果被观察到过于保守。在流形学习中,取而代之的是假设数据是从未知流形采样的;即,流形由数据本身定义。在此未知流形上的函数逼近是一个两阶段的过程:首先,使用图拉普拉斯来逼近该流形上的Laplace-Beltrami算子(及其特征分解),然后,使用特征函数来逼近目标函数。在这篇文章中,我们提出了一种更直接的方法来逼近未知的数据定义的流形上的函数,而不需要计算某些算子的特征分解,并用流形的维度来估计逼近程度。这导致在使用深度网络的函数逼近中得到类似的结果,其中每个通道评估可能未知流形上的高斯网络。
In much of the literature on function approximation by deep networks, the function is assumed to be defined on some known domain, such as a cube or sphere. In practice, the data might not be dense on these domains, and therefore, the approximation theory results are observed to be too conservative. In manifold learning, one assumes instead that the data is sampled from an unknown manifold; i.e., the manifold is defined by the data itself. Function approximation on this unknown manifold is then a two stage procedure: first, one approximates the Laplace-Beltrami operator (and its eigen-decomposition) on this manifold using a graph Laplacian, and next, approximates the target function using the eigen-functions. In this paper, we propose a more direct approach to function approximation on unknown, data defined manifolds without computing the eigen-decomposition of some operator, and estimate the degree of approximation in terms of the manifold dimension. This leads to similar results in function approximation using deep networks where each channel evaluates a Gaussian network on a possibly unknown manifold.
DOI: 10.3389/fams.2020.00031
发表时间: 2019-01
期刊: --
影响因子: --
作者:
H. Mhaskar;A. Cloninger;Xiuyuan Cheng
通讯作者: H. Mhaskar;A. Cloninger;Xiuyuan Cheng