哈尔滨工业大学（深圳）学术讲座

演讲人Speaker：武汉大学数学统计学院 焦雨领副教授

题目Title: Theoretical study on deep learning: approximation, generalization, optimization, representation and generation

时间Date： 2023 年 09 月 01 日       Time：09:30-10:30

地点Venue：T2栋 304 室

内容摘要Abstract：In the first part of this talk, I will discuss some theoretical studies on deep learning with a focus on approximation, generalization, optimization, and representation. In particular, I will cover error analysis with over-parameterization. In the second part, I will delve into sampling and generative learning via and SDE and ODE.

个人简介(About the speaker): 焦雨领，男，武汉大学数学统计学院副教授、博导.主要研究方向科学计算、机器学习.任ACM Transaction on Probabilistic Machine Learning 编委。在包括 SIAM 系列 （SINUM、SICS、SIMA、SICON）、Applied and Computational Harmonic Analysis、Inverse Problems, Journal of the American Statistical Association、 Statistical Science: A Review Journal of IMS, IEEE Transactions on Signal Processing， Journal of Machine   Learning Research、ICML 、NeurIPS、COLT等在内的期刊和会议上发表了40余篇论文.