题  目：A Unified Framework for Non-Convex Low-Rank Matrix Recovery Problems

内容简介：The challenge of recovering low-rank matrices from linear samples is a common issue in various fields, including machine learning, imaging, signal processing, and computer vision. Non-convex algorithms have proven to be highly effective and efficient for low-rank matrix recovery, providing theoretical guarantees despite the potential for local minima. This talk presents a unifying framework for non-convex low-rank matrix recovery algorithms using Riemannian gradient descent. We demonstrate that numerous well-known non-convex low-rank matrix recovery algorithms can be considered special instances of Riemannian gradient descent, employing distinct Riemannian metrics and retraction operators. Consequently, we can pinpoint the optimal metrics and develop the most efficient non-convex algorithms. To illustrate this, we introduce a new preconditioned Riemannian gradient descent algorithm, which accelerates matrix completion tasks by more than ten times compared to traditional methods.

报告人：蔡剑锋

报告人简介：香港科技大学数学系教授，主要研究兴趣为信号，图像和数据的理论和算法基础。他在矩阵恢复，图像重构和成像算法等领域，取得了一系列开创性的科研成果。其关于矩阵补全的SVT算法对学术研究和实际应用产生重要影响，该文章谷歌被引次数超6000次。蔡剑锋教授关于图像重构的工作发表于被誉为数学四大期刊之一的Journal of the AMS。蔡剑锋教授在2017年和2018年被评为全球高被引学者，学术文章总被引超13000次。

时  间：2024年1月2日（周二）下午16：30 开始

地  点：南海楼124室

热烈欢迎广大师生参加!

信息科学技术学院/网络空间安全学院

2023年12月29日