Local Rademacher Complexity: sharper risk bounds with and without unlabeled samples.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date: Feb 16, 2015

Abstract

We derive in this paper a new Local Rademacher Complexity risk bound on the generalization ability of a model, which is able to take advantage of the availability of unlabeled samples. Moreover, this new bound improves state-of-the-art results even when no unlabeled samples are available.

Authors

  • Luca Oneto
    DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Luca.Oneto@unige.it.
  • Alessandro Ghio
    DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Alessandro.Ghio@unige.it.
  • Sandro Ridella
    DITEN - University of Genova, Via Opera Pia 11A, I-16145 Genova, Italy. Electronic address: Sandro.Ridella@unige.it.
  • Davide Anguita
    DIBRIS - University of Genova, Via Opera Pia 13, I-16145 Genova, Italy. Electronic address: Davide.Anguita@unige.it.

Keywords

External Resources

Popular Topics
Recent Journals