【廿周年院庆学术报告119】 · 【和山数学论坛第396期】

一、报告题目：Barron Space for Graph Convolution Neural Networks

二、报告人：孙颀彧 教授

三、时 间： 2023年12月22日 (星期五) 下午 15:00—16:00

四、地  点：闻理园A4-309

报告摘要：Graph convolutional neural network  (GCNN) operates on graph domain and it has  achieved a superior performance to accomplish a wide range of tasks. 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 GCNNs, and learnability of functions in the Barron space from their random samples.

报告人简介：孙颀彧教授，中佛罗里达大学。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, Transactionof American Mathematical Society, Applied and Computational Harmonic Analysis, Advancesin Computational Mathematic, IEEE Transaction on Information Theory, IEEETransaction on Signal Processing, Journal of Fourier Analysis and Applications等发表论文100多篇.担任Frontiers in Applied Mathematics and Statistics, Sampling Theory in Signal and Imaging Processing, Numerical Functional Analysisand Optimization, Advances in Computational Mathematics等期刊的编委。孙教授发表学术论文160多篇，文章引用率3000多次。

欢迎感兴趣的老师和同学参加！联系人：房启全