Nonparametric IPSS: fast, flexible feature selection with false discovery control.

Journal: Bioinformatics (Oxford, England)
Published Date: May 6, 2025

Abstract

MOTIVATION: Feature selection is a critical task in machine learning and statistics. However, existing feature selection methods either (i) rely on parametric methods such as linear or generalized linear models, (ii) lack theoretical false discovery control, or (iii) identify few true positives.

Authors

  • Omar Melikechi
    Department of Biostatistics at Harvard University, Boston, MA, 02115 USA.
  • David B Dunson
    Department of Statistical Science at Duke University, Durham, NC, 27708 USA.
  • Jeffrey W Miller
    Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, Massachusetts, USA.

Keywords

External Resources

Popular Topics
Recent Journals