Algorithmic statistics revisited

Nikolay Vereshchagin 1 Alexander Shen 2
2 ESCAPE - Systèmes complexes, automates et pavages
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : The mission of statistics is to provide adequate statistical hypotheses (models) for observed data. But what is an "adequate" model? To answer this question, one needs to use the notions of algorithmic information theory. It turns out that for every data string $x$ one can naturally define "stochasticity profile", a curve that represents a trade-off between complexity of a model and its adequacy. This curve has four different equivalent definitions in terms of (1)~randomness deficiency, (2)~minimal description length, (3)~position in the lists of simple strings and (4)~Kolmogorov complexity with decompression time bounded by busy beaver function. We present a survey of the corresponding definitions and results relating them to each other.
Document type :
Book sections
Complete list of metadatas

https://hal-lirmm.ccsd.cnrs.fr/lirmm-01233770
Contributor : Alexander Shen <>
Submitted on : Wednesday, November 25, 2015 - 5:22:03 PM
Last modification on : Wednesday, September 4, 2019 - 5:36:02 PM

Links full text

Identifiers

Collections

Citation

Nikolay Vereshchagin, Alexander Shen. Algorithmic statistics revisited. Measures of Complexity. Festschrift for Alexey Chervonenkis, Part IV, pp.235-252, 2015, 978-3-319-21851-9. ⟨10.1007/978-3-319-21852-6_17⟩. ⟨lirmm-01233770⟩

Share

Metrics

Record views

120