Talk page

Title:
Some Statistical Results on Deep Learning: Interpolation, Optimality and Sparsity

Speaker:
Guang Cheng

Abstract:
This talk discusses three aspects of deep learning from a statistical perspective: interpolation, optimality and sparsity. The first one attempts to interpret the double descent phenomenon by precisely characterizing a U-shaped curve within the “over-fitting regime,” while the second one focuses on the statistical optimality of neural network classification in a student-teacher framework. This talk is concluded by proposing sparsity induced training of neural network with statistical guarantee.

Link:
https://www.ias.edu/video/machinelearning/2019/1113-GuangCheng