Sparse Zero-Sum Games as Stable Functional Feature Selection

PloS One
Nataliya SokolovskaJean-Daniel Zucker

Abstract

In large-scale systems biology applications, features are structured in hidden functional categories whose predictive power is identical. Feature selection, therefore, can lead not only to a problem with a reduced dimensionality, but also reveal some knowledge on functional classes of variables. In this contribution, we propose a framework based on a sparse zero-sum game which performs a stable functional feature selection. In particular, the approach is based on feature subsets ranking by a thresholding stochastic bandit. We provide a theoretical analysis of the introduced algorithm. We illustrate by experiments on both synthetic and real complex data that the proposed method is competitive from the predictive and stability viewpoints.

References

Mar 9, 2007·Bioinformatics·James Z WangChin-Fu Chen
Sep 18, 2010·IEEE Transactions on Pattern Analysis and Machine Intelligence·Petr Somol, Jana Novovicová
Aug 30, 2013·Nature·Aurélie CotillardStanislav Dusko Ehrlich
Dec 11, 2013·BioMed Research International·Nicoletta DessìBarbara Pes

❮ Previous
Next ❯

Methods Mentioned

BETA
feature extraction

Related Concepts

Related Feeds

Birth Defects

Birth defects encompass structural and functional alterations that occur during embryonic or fetal development and are present since birth. The cause may be genetic, environmental or unknown and can result in physical and/or mental impairment. Here is the latest research on birth defects.

Related Papers

Bulletin of Mathematical Biology
P H Richter
Proceedings of the National Academy of Sciences of the United States of America
L S Shapley
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adrian BarbuGary Gramajo
© 2021 Meta ULC. All rights reserved