演讲人： Weijie Su the Wharton School, University of Pennsylvania
时间： 2023-07-10 14:00-2023-07-10 15:00
地点：FIT 1-222(主持人: Yuhao Wang)
内容：

The law of equi-separation is a pervasive empirical phenomenon that describes how data are separated according to their class membership from the bottom to the top layer in a well-trained neural network. We will show that, through extensive computational experiments, neural networks improve data separation through layers in a simple exponential manner. This law leads to roughly equal ratios of separation that a single layer is able to improve, thereby showing that all layers are created equal. We will conclude the talk by discussing the implications of this law on the interpretation, robustness, and generalization of deep learning, as well as on the inadequacy of some existing approaches toward demystifying deep learning. This is based on joint work with Hangfeng He (arXiv:2210.17020).

个人简介:

Weijie Su is an Associate Professor at the Wharton School, University of Pennsylvania, with secondary appointments in the Department of Computer and Information Science and Department of Mathematics. He is a co-director of Penn Research in Machine Learning Center. Prior to joining Penn, he received his Ph.D. from Stanford University in 2016 and his bachelor’s degrees in mathematics and economics from Peking University in 2011. His research interests span deep learning theory, privacy-preserving data analysis, data valuation, mathematical optimization, and mechanism design. He is a recipient of the Stanford Theodore Anderson Dissertation Award in 2016, an NSF CAREER Award in 2019, a Sloan Research Fellowship in 2020, the SIAM Early Career Prize in Data Science in 2022, and the IMS Peter Gavin Hall Prize in 2022.