An NEPv Approach for Feature Selection via Orthogonal OCCA with the (2,1)-norm Regularization

TL;DR

This paper introduces OCCA-FS, a new feature selection method based on orthogonal canonical correlation analysis with (2,1)-norm regularization, solved via a nonlinear eigenvalue problem approach, demonstrating superior performance.

Contribution

It proposes a novel NEPv-based algorithm for feature selection using orthogonal OCCA with (2,1)-norm regularization, ensuring convergence and improved classification accuracy.

Findings

OCCA-FS outperforms existing feature selection methods in classification tasks.

The method guarantees monotonic convergence of the objective function.

Numerical experiments confirm the effectiveness and superiority of OCCA-FS.

Abstract

A novel feature selection model via orthogonal canonical correlation analysis with the $(2,1)$-norm regularization is proposed, and the model is solved by a practical NEPv approach (nonlinear eigenvalue problem with eigenvector dependency), yielding a feature selection method named OCCA-FS. It is proved that OCCA-FS always produces a sequence of approximations with monotonic objective values and is globally convergent. Extensive numerical experiments are performed to compare OCCA-FS against existing feature selection methods. The numerical results demonstrate that OCCA-FS produces superior classification performance and often comes out on the top among all feature selection methods in comparison.