The Modified Increment Method for Eigenspace Model
Year: 2021
Type: article
Abstract: Eigenspace is a convenient way to represent sets of observations with widespread applications, so it is necessary to accurately calculate the eigenspace of data. With the advent of the era of big data, the increasing and updating of data bring great challenges to the solution of eigenspace. Hall, et al. [1], proposed that the incremental method could update the eigenspace of data online, which reduces computational costs and storage space. In this paper, the updating coefficient of the sample covariance matrix in an incremental method is modified. Numerical analysis shows that the modified updating form has better performance.
Authors: Chunjie Wei, Jian Wang
Language: English
Topic: Matrix Theory and Algorithms
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W3193321039
