基于集中的低秩矩阵重构保证][Concentration-Based Guarantees for Low-Rank Matrix Reconstruction]

基于集中的低秩矩阵重构保证 Concentration-Based Guarantees for Low-Rank Matrix Reconstruction


课程网址:	http://videolectures.net/colt2011_foygel_matrix/
主讲教师:	Rina Foygel
开课单位:	芝加哥大学
开课时间:	2011-08-02
课程语种:	英语
中文简介:	我们考虑近似重建一个部分观测到的近似低秩矩阵的问题。这个问题最近得到了广泛的关注，主要是使用跟踪规范来代替等级。本文研究了采用跟踪范数和较少研究的极大范数进行低秩矩阵重构的方法，并在分析这些范数的单位球复杂度的基础上给出了重构保证。我们展示了它们在几个方面如何优于最近发布的基于专门分析的保证。
课程简介:	We consider the problem of approximately reconstructing a partially-observed, approximately low-rank matrix. This problem has received much attention lately, mostly using the trace-norm as a surrogate to the rank. Here we study low-rank matrix reconstruction using both the trace-norm, as well as the less-studied max-norm, and present reconstruction guarantees based on existing analysis on the Rademacher complexity of the unit balls of these norms. We show how these are superior in several ways to recently published guarantees based on specialized analysis.
关键词:	低秩矩阵; 跟踪规范; 极大范数; 低秩矩阵重构
课程来源:	视频讲座网
最后编审:	2019-10-17：cwx
阅读次数:	110

境外开放课程导航