Speaker: Jian Huang, Chair Professor of Data Science and Analytics, Department of Applied Mathematics, the Hong Kong Polytechnic University

Date: December 21, 2023

Time: 15:00-16:00

Location: Tencent Meeting: 518 701 870

Sponsor: Zhongtai Securities Institute for Financial Studies, Shandong University

Abstract:

Deep learning has achieved remarkable success in a wide range of applications and has been applied to analyzing high-dimensional data in many fields of scientific research. Therefore, it would be useful to understand why deep learning has been so successful and what its main advantages are over the traditional nonparametric methods developed over the decades, if any. In this talk, we try to explain some advantages of deep learning by considering the approximation power of deep neural networks and generalization errors of deep learning methods. Using nonparametric regression and conditional generative learning as examples, we illustrate deep learning approaches to dealing with some high-dimensional statistical problems.

For more information, please visit:

https://mathfinance.sdu.edu.cn/info/1273/7372.htm