A Random Matrix Approach to Neural Networks:
From Linear to Nonlinear,
and from Shallow to Deep
报告专家：廖振宇 副研究员 （华中科技大学）
报告时间：10月20日（周一）10:30-11:30
报告地点：腾讯会议：979-107-906
报告摘要：
Deep neural networks have become the cornerstone of modern machine learning, yet their multi-layer structure, nonlinearities, and intricate optimization processes pose considerable theoretical challenges.
In this talk, I will review recent advances in random matrix analysis that shed new light on these complex ML models. Starting with the foundational case of linear regression, I will demonstrate how the proposed analysis extends naturally to shallow nonlinear and ultimately deep nonlinear network models. I will also discuss practical implications (e.g., compressing and/or designing "equivalent" NN models) that arise from these theoretical insights.
The talk is based on a recent review paper https://arxiv.org/abs/2506.13139 joint with Michael W. Mahoney.
专家简介：
廖振宇，于法国巴黎萨克雷大学获数学与计算机博士学位，后在美国加州大学伯克利分校统计系和ICSI从事博士后研究工作，2021年起至今在华中科技大学电信学院工作，任副研究员。
主要从事“面向高维数据的大规模机器学习理论和方法”研究，发展非线性高维统计学和随机矩阵理论以解决大规模机器学习中的基础理论问题，研究成果形成论文三十余篇，发表在ICML、NeurIPS、ICLR、COLT、IEEE TSP和AAP等机器学习和数据处理的会议与期刊，合著专著Random Matrix Methods for Machine Learning。
任中国现场统计研究会随机矩阵理论与应用分会副秘书长、大数据统计分会理事。
邀请人：李世豪
