报告题目：Function Spaces in Neural Networks: Theory and Applications

报告人：陆帅，复旦大学

报告时间：2026年05月11日（周一），9：00-11：00

腾讯会议：#789-350-394

报告摘要：We investigate several norm spaces derived from neural network architectures, including (extended) Barron spaces, variation spaces, Radon-BV spaces, and spectral Barron spaces. This talk systematically explores the relationships among these spaces, develops new analytical tools across different frameworks, and examines their applications in partial differential equations, as well as in related inverse problems and regularization methods. This is a joint series of works in collaboration with Mourad Choulli (U. Lorraine), Yuanyuan Li (CUHK), Peter Mathé (WIAS), Sergei V. Pereverzev (RICAM) and Hiroshi Takase (Kyushu U.).

报告人简介：陆帅，复旦大学数学科学学院教授、博导，主要从事数学物理反问题计算方法与数学理论的研究，特别是反问题正则化方法收敛性分析及偏微分方程反问题稳定性理论等。至今在Math. Ann. Inverse Problems、SIAM系列、Numer. Math.、Math. Comp.等权威期刊共发表学术论文六十余篇，合作出版英文学术专著一本。2019年获基金委青A项目资助，现任Inverse Problems等多个国际期刊的编委，国际反问题联盟执行委员会委员。曾获上海市自然科学奖一等奖（排名第2）。