English

A scale-dependent notion of effective dimension

Machine Learning 2020-01-30 v1 Machine Learning

Abstract

We introduce a notion of "effective dimension" of a statistical model based on the number of cubes of size 1/n1/\sqrt{n} needed to cover the model space when endowed with the Fisher Information Matrix as metric, nn being the number of observations. The number of observations fixes a natural scale or resolution. The effective dimension is then measured via the spectrum of the Fisher Information Matrix regularized using this natural scale.

Keywords

Cite

@article{arxiv.2001.10872,
  title  = {A scale-dependent notion of effective dimension},
  author = {Oksana Berezniuk and Alessio Figalli and Raffaele Ghigliazza and Kharen Musaelian},
  journal= {arXiv preprint arXiv:2001.10872},
  year   = {2020}
}
R2 v1 2026-06-23T13:24:02.875Z