Neural Operators: Abstract Framework and Multigrid Structure
数学专题报告
报告题目(Title):Neural Operators: Abstract Framework and Multigrid Structure
报告人(Speaker):何俊材 (清华大学)
地点(Place):后主楼1124
时间(Time):2025年6月26日 (周四) 下午14:00-14:40
邀请人(Inviter):段玉萍
报告摘要
In this talk, we will present recent results on applying multigrid structures to neural operators for problems in numerical PDEs. First, we will discuss some basic background on operator learning, including the problem setup, a uniform abstract framework, and a general universal approximation result. Motivated by the general definition of neural operators, we propose MgNO, which utilizes multigrid structures to parameterize these linear operators between neurons, offering a new and concise architecture in operator learning. For the implementation issue of MgNO, we will illustrate MgNet as a unified framework for convolutional neural networks and multigrid methods. This approach provides both mathematical rigor and practical expressivity, with many interesting numerical properties and observations.
主讲人简介
何俊材本科毕业于四川大学,博士毕业于北京大学。2019年至2020年,在宾夕法尼亚州立大学从事博士后研究;2020年至2022年,在得克萨斯大学奥斯汀分校担任R. H. Bing Instructor;2022年至2025年,在沙特阿卜杜拉国王科技大学任研究科学家;2025年2月,加入清华大学丘成桐数学科学中心,任助理教授。他的主要研究方向是科学计算与机器学习,涵盖深度神经网络的理论分析、算法设计与实际应用等方面。