报告时间：2021年10月22日

                晚上20:30-21:30

报告地点：腾讯会议

             （会议ID：916 668 989）

报告嘉宾：苏炜杰

报告主题：A Top-Down Approach Toward Understanding Deep Learning

报告摘要

A Top-Down Approach Toward Understanding Deep Learning

The remarkable development of deep learning over the past decade relies heavily on sophisticated heuristics and tricks. To better exploit its potential in the coming decade, perhaps a rigorous framework for reasoning deep learning is needed, which however is not easy to build due to the intricate details of modern neural networks. For near-term purposes, a practical alternative is to develop a mathematically tractable surrogate model that yet maintains many characteristics of deep learning models. This talk introduces a model of this kind as a tool toward understanding deep learning. The effectiveness of this model, which we term the Layer-Peeled Model, is evidenced by two use cases. First, we use this model to explain an empirical pattern of deep learning recently discovered by David Donoho and his students. Moreover, this model predicts a hitherto unknown phenomenon that we term Minority Collapse in deep learning training. This is based on joint work with Cong Fang, Hangfeng He, and Qi Long.

个人简介

苏炜杰, 沃顿商学院统计学助理教授，2011年毕业于北京大学数学科学学院，2016年获斯坦福大学统计学博士学位，其间获得理论统计学Theodore Anderson 论文奖。主要从事机器学习和高维统计等课题的研究，2019年获得美国国家自然科学基金颁发的Faculty Early Career Development Award (NSF CAREER Award)，即美国国家自然科学基金青年科学家奖，该奖授予职业初期在自然科学领域做出比较重要贡献的青年教授。