时 间：2023年5月11日（周四）15：00
地 点: 腾讯会议：632170570
题 目：Theoretical study on deep learning: approximation, generalization, optimization, representation and generation
报告人：焦雨领 武汉大学副教授
主持人：谌自奇 研究员
主 办：统计学院
摘 要：
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 the concept of Gaussian stochastic interpolations and their applications, including the derivation of functional inequality with dimension-free constants, as well as sampling and generative learning.
报告人简介：
Dr. Yuling Jiao is an Associate Professor in the School of Mathematics and Statistics in Wuhan University. His research interests include machine learning, scientific computing. His research works were published in the Annals of Statistics, Journal of the American Statistical Association, Statistical Science: A Review Journal of IMS, SIAM Journal on Mathematical Analysis, SIAM Journal on Numerical Analysis, SIAM Journal on Scientific Computing, Applied and Computational Harmonic Analysis, Inverse Problems, IEEE Transactions on Signal Processing, Journal of Machine Learning Research, ICML , NeurIPS.