学术报告会：Barron Space for Graph Convolution Neural Networks

报告题目：Barron Space for Graph Convolution Neural Networks

报 告 人：孙颀彧（美国佛罗里达中央大学   教授）

报告时间：2024年6月15日周五16：30

报告地点：S3-407

摘要：In this talk, we introduce a Barron space of functions on a compact domain of graph signals, discuss its various properties, such as reproducing kernel Banach space property and universal approximation property. We will also discuss well approximation property of functions in the Barron、space by outputs of some graph convolution neural networks, and learnability of functions in the Barron space from their random samples.

个人简介：

孙颀彧，美国佛罗里达中央大学数学系教授。主要从事傅里叶分析、小波分析、框架理论、信号采样和处理等方面的研究工作。在国际顶尖权威杂志Memoirs of American Mathematical Society, Transaction of American Mathematical Society, Applied and Computational Harmonic Analysis, Advances in Computational Mathematics, IEEE Transaction on Information Theory, IEEE Transaction on Signal Processing, Journal of Fourier Analysis and Applications等发表论文一百多篇，被引三千多次。先后担任Frontiers in Applied Mathematics and Statistics, Sampling Theory in Signal and Imaging Processing, Numerical Functional Analysis and Optimization, Advances in Computational Mathematics等期刊的编委。