English

Local shrinkage rules, Levy processes, and regularized regression

Methodology 2011-04-26 v2 Statistics Theory Statistics Theory

Abstract

We use Levy processes to generate joint prior distributions, and therefore penalty functions, for a location parameter as p grows large. This generalizes the class of local-global shrinkage rules based on scale mixtures of normals, illuminates new connections among disparate methods, and leads to new results for computing posterior means and modes under a wide class of priors. We extend this framework to large-scale regularized regression problems where p>n, and provide comparisons with other methodologies.

Keywords

Cite

@article{arxiv.1010.3390,
  title  = {Local shrinkage rules, Levy processes, and regularized regression},
  author = {Nicholas G. Polson and James G. Scott},
  journal= {arXiv preprint arXiv:1010.3390},
  year   = {2011}
}
R2 v1 2026-06-21T16:29:34.198Z