@inproceedings{1a04267452d047109432efd9d2befc32,
title = "A feature selection algorithm capable of handling extremely large data dimensionality",
abstract = "With the advent of high throughput technologies, feature selection has become increasingly important in a wide range of scientific disciplines. We propose a new feature selection algorithm that performs extremely well in the presence of a huge number of irrelevant features. The key idea is to decompose an arbitrarily complex nonlinear models into a set of locally linear ones through local learning, and then estimate feature relevance globally within a large margin framework. The algorithm is capable of processing many thousands of features within a few minutes on a personal computer, yet maintains a close-to-optimum accuracy that is nearly insensitive to a growing number of irrelevant features. Experiments on eight synthetic and real-world datasets are presented that demonstrate the effectiveness of the algorithm.",
author = "Yijun Sun and Sinisa Todorovic and Steve Goodison",
year = "2008",
doi = "10.1137/1.9781611972788.48",
language = "English (US)",
isbn = "9781605603179",
series = "Society for Industrial and Applied Mathematics - 8th SIAM International Conference on Data Mining 2008, Proceedings in Applied Mathematics 130",
publisher = "Society for Industrial and Applied Mathematics Publications",
pages = "530--540",
booktitle = "Society for Industrial and Applied Mathematics - 8th SIAM International Conference on Data Mining 2008, Proceedings in Applied Mathematics 130",
address = "United States",
note = "8th SIAM International Conference on Data Mining 2008, Applied Mathematics 130 ; Conference date: 24-04-2008 Through 26-04-2008",
}