Feature Selection via Binary Simultaneous Perturbation Stochastic Approximation

TL;DR

This paper introduces a novel wrapper feature selection method using binary simultaneous perturbation stochastic approximation (BSPSA), which efficiently handles large datasets with thousands of features by approximating gradients through stochastic perturbations.

Contribution

The paper presents a new BSPSA-based wrapper approach for feature selection that is computationally feasible and effective for very high-dimensional datasets, outperforming traditional methods.

Findings

BSPSA outperforms genetic algorithms and sequential methods in accuracy.

BSPSA is computationally feasible for datasets with tens of thousands of features.

Selected features by BSPSA lead to better classification performance.

Abstract

Feature selection (FS) has become an indispensable task in dealing with today's highly complex pattern recognition problems with massive number of features. In this study, we propose a new wrapper approach for FS based on binary simultaneous perturbation stochastic approximation (BSPSA). This pseudo-gradient descent stochastic algorithm starts with an initial feature vector and moves toward the optimal feature vector via successive iterations. In each iteration, the current feature vector's individual components are perturbed simultaneously by random offsets from a qualified probability distribution. We present computational experiments on datasets with numbers of features ranging from a few dozens to thousands using three widely-used classifiers as wrappers: nearest neighbor, decision tree, and linear support vector machine. We compare our methodology against the full set of features as well as a binary genetic algorithm and sequential FS methods using cross-validated classification error rate and AUC as the performance criteria. Our results indicate that features selected by BSPSA compare favorably to alternative methods in general and BSPSA can yield superior feature sets for datasets with tens of thousands of features by examining an extremely small fraction of the solution space. We are not aware of any other wrapper FS methods that are computationally feasible with good convergence properties for such large datasets.