The robustness in Learning theory
组织者
丘成栋
演讲者
康家熠
时间
2023年05月29日 16:00 至 16:30
地点
数学系理科楼A-203
摘要
In this report, I shall introduce the theory robustness of neural networks. Extensive studies have been devoted to developing neural networks with certified robustness guarantees. Existing approaches can be mainly divided into the following three categories: certified defenses via randomized smoothing, certified defenses for standard networks and certified defenses using Lipschitz networks. I will introduce recent work on robustness of neural networks.
演讲者介绍
Jiayi Kang received his Ph.D. in Mathematics from Tsinghua University in 2024. He joined the Beijing Institute of Mathematical Sciences and Applications (BIMSA) as an Assistant Researcher in July 2024, and became an Assistant Professor at the Hetao Institute for Mathematical and Interdisciplinary Sciences (HIMIS) in November 2025.
His research focuses on the intersection of deep learning, nonlinear filtering, and computational biology. His main research interests include: neural network-based filtering algorithms and their mathematical foundations, sampling methods in Wasserstein geometry, nonlinear filtering theory (including the Yau-Yau method) and its applications in climate science and other fields, as well as computational genomics and evolutionary system modeling. He is committed to solving complex problems in science and engineering using mathematical and machine learning methods.