Stability properties of feature selection measures
Teoriâ veroâtnostej i ee primeneniâ, Tome 69 (2024) no. 1, pp. 33-45
Voir la notice de l'article provenant de la source Math-Net.Ru
In this paper, we prove that the monotonicity property of the stability measure
for the feature (factor) selection introduced by Nogueira, Sechidis, and Brown
[J. Mach. Learn. Res., 18 (2018), pp. 1–54] may not hold. Another
monotonicity property takes place. We also show the cases in which it is
possible to compare by certain parameters the matrices describing the operation
of algorithms for identifying relevant features.
Keywords:
selection of relevant features, stability measures of the feature selection algorithm, properties of stability measures.
@article{TVP_2024_69_1_a1,
author = {A. V. Bulinski},
title = {Stability properties of feature selection measures},
journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
pages = {33--45},
publisher = {mathdoc},
volume = {69},
number = {1},
year = {2024},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/TVP_2024_69_1_a1/}
}
A. V. Bulinski. Stability properties of feature selection measures. Teoriâ veroâtnostej i ee primeneniâ, Tome 69 (2024) no. 1, pp. 33-45. http://geodesic.mathdoc.fr/item/TVP_2024_69_1_a1/