On Phase Transitions in Learning Sparse Networks

  • Goele Hollandersa, Geert Jan Bexa, Marc Gyssensa, Ronald L. Westrab, Karl Tuylsb
  • Published 2007

Abstract

In this paper [1] we study the identification of sparse interaction networks, from a given set of observations, as a machine learning problem. An example of such a network is a sparse gene-protein interaction network, for more details see [2]. Sparsity means that we are provided with a small data set and a high number of unknown components of the system, most of which are zero. Under these circumstances, a model needs to be learned that fits the underlying system, capable of generalization. This corresponds to the student-teacher setting in machine learning.

4 Figures and Tables

Cite this paper

@inproceedings{Hollandersa2007OnPT, title={On Phase Transitions in Learning Sparse Networks}, author={Goele Hollandersa and Geert Jan Bexa and Marc Gyssensa and Ronald L. Westrab and Karl Tuylsb}, year={2007} }