English

Topological regularization with information filtering networks

Machine Learning 2021-11-02 v2 Machine Learning

Abstract

A methodology to perform topological regularization via information filtering network is introduced. This methodology can be directly applied to covariance selection problem providing an instrument for sparse probabilistic modeling with both linear and non-linear multivariate probability distributions such as the elliptical and generalized hyperbolic families. It can also be directly implemented for L0L_0-norm regularized multicollinear regression. In this paper, I describe in detail an application to sparse modeling with multivariate Student-t. A specific L0L_0-norm regularized expectation-maximization likelihood maximization procedure is proposed for this sparse Student-t case. Examples with real data from stock prices log-returns and from artificially generated data demonstrate the applicability, performances, and potentials of this methodology.

Keywords

Cite

@article{arxiv.2005.04692,
  title  = {Topological regularization with information filtering networks},
  author = {Tomaso Aste},
  journal= {arXiv preprint arXiv:2005.04692},
  year   = {2021}
}

Comments

17 pages , 4 figures, 1 table

R2 v1 2026-06-23T15:26:11.844Z