A Novel Iterative Method for Principal Component Analysis

Principal Component Analysis (PCA) is a statistical method used for identifying key patterns from a given dataset and reducing its dimensions, while retaining most of the original information. The power method, which is one of the most well-known algorithms for PCA, is simple and easy to implement. However it obtains the specified number of principal components one by one. In this paper, we propose a novel iterative method for PCA, which is expressed as a system of nonlinear difference equations. Unlike the power method, the proposed method can obtain the specified number of principal components in parallel. We also show results of numerical experiments and theoretical analysis to verify the validity of the proposed method.

© 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

This fulltext file will be available in Oct. 2028.