On convergence of fast subspace tracking based on novel information criterion

Da Zheng Feng, Wei Xing Zheng

Research output: Chapter in Book / Conference PaperConference Paperpeer-review

Abstract

The averaging differential equation associated with a family of fast subspace tracking algorithms based on a novel information criterion (NIC) is known as the NIC flow. This paper investigates global exponential convergence of the NIC flow. It is shown that at a characterized exponential speed the NIC flow globally converges to the principal subspace spanned by the eigenvectors corresponding to the principal eigenvalues of the covariance matrix of a high dimensional data stream. The given exponential convergence rate may be a very tight estimate. It is also demonstrated that the convergence speed of the NIC flow is typically faster than that of the well-known Oja's flow. Numerical results are presented to support the theoretical analysis.

Original languageEnglish
Title of host publicationProceedings of 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03
Pages261-264
Number of pages4
DOIs
Publication statusPublished - 2003
Event2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03 - Nanjing, China
Duration: 14 Dec 200317 Dec 2003

Publication series

NameProceedings of 2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03
Volume1

Conference

Conference2003 International Conference on Neural Networks and Signal Processing, ICNNSP'03
Country/TerritoryChina
CityNanjing
Period14/12/0317/12/03

Fingerprint

Dive into the research topics of 'On convergence of fast subspace tracking based on novel information criterion'. Together they form a unique fingerprint.

Cite this