Skip to Main content Skip to Navigation
Conference papers

Learning linear classifiers with ternary weights from Metagenomic Data

Abstract : Motivated by recent researches in metagenomic classification tasks, this paper investigates the problem of finding interpretable concepts from training data in which the number of features is larger than the number of samples. In this setting, the classification problem is modeled as a combinatorial optimization problem, in which the aim of the learner is to find a {−1, 0, +1}-weighted linear threshold function that minimizes the hinge loss induced from the training data. Two methods are analyzed and experimented: convex optimization that applies randomized rounding to the optimum in the convex hull of the concept class, and supermodular minimization that performs a local search in the concept class, with a guarantee on the approximate solution for the subclass of {0, 1}-weighted threshold functions.
Document type :
Conference papers
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download
Contributor : Laurent Bougrain Connect in order to contact the contributor
Submitted on : Thursday, October 25, 2012 - 3:10:34 PM
Last modification on : Friday, August 5, 2022 - 3:02:57 PM
Long-term archiving on: : Monday, January 28, 2013 - 1:40:51 PM


Files produced by the author(s)


  • HAL Id : hal-00745449, version 1


Yann Chevaleyre, Frédéric Koriche, Jean-Daniel Zucker. Learning linear classifiers with ternary weights from Metagenomic Data. Conférence Francophone sur l'Apprentissage Automatique - CAp 2012, Laurent Bougrain, May 2012, Nancy, France. 16 p. ⟨hal-00745449⟩



Record views


Files downloads