学术报告报告题目： On the Loss Landscape and Error Bound of Regularized Deep Linear Networks
报 告 人：汪鹏 助理教授
报告时间：2026年7月2日（星期四）下午14:00-15:00
报告地点： 37号楼3A01
邀 请 人： 刘晓霞 副教授
欢迎广大师生前往！
数学虎门体育app下载官网
2026年7月1日
报告摘要：
The optimization foundations of deep linear networks have received significant attention lately. However, due to the non-convexity and hierarchical structure, analyzing the regularized loss of deep linear networks remains a challenging task. In this work, we study the local geometric landscape of the regularized squared loss of deep linear networks, providing a deeper understanding of its optimization properties. Specifically, we characterize the critical point set and establish an error-bound property for all critical points under mild conditions. Notably, we identify the sufficient and necessary conditions under which the error bound holds. To support our theoretical findings, we conduct numerical experiments demonstrating that gradient descent exhibits linear convergence when optimizing the regularized loss of deep linear networks.
报告人简介：
汪鹏，澳门大学计算机与信息科学系，助理教授。曾在密歇根大学担任博士后研究员，合作导师为Laura Balzano和Qing Qu教授。他在香港中文大学系统工程与工程管理系获得博士学位，导师为Anthony Man-Cho So教授。他的研究兴趣主要是优化、机器学习与人工智能的交叉领域。当前，他的研究重点在于探索深度学习的优化基。喽窖澳Ｐ、扩散模型以及大型语言模型。