Hypotheses testing on infinite random graphs

Daniil Ryabko 1
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : Drawing on some recent results that provide the formalism necessary to definite stationarity for infinite random graphs, this paper initiates the study of statistical and learning questions pertaining to these objects. Specifically, a criterion for the existence of a consistent test for complex hypotheses is presented, generalizing the corresponding results on time series. As an application, it is shown how one can test that a tree has the Markov property, or, more generally, to estimate its memory.
Type de document :
Communication dans un congrès
ALT 2017 - 28th International Conference on Algorithmic Learning Theory, Oct 2017, kyoto, Japan. pp.1-12
Liste complète des métadonnées

https://hal.inria.fr/hal-01627330
Contributeur : Daniil Ryabko <>
Soumis le : mercredi 1 novembre 2017 - 09:40:55
Dernière modification le : mardi 3 juillet 2018 - 11:35:53

Lien texte intégral

Identifiants

  • HAL Id : hal-01627330, version 1
  • ARXIV : 1708.03131

Citation

Daniil Ryabko. Hypotheses testing on infinite random graphs. ALT 2017 - 28th International Conference on Algorithmic Learning Theory, Oct 2017, kyoto, Japan. pp.1-12. 〈hal-01627330〉

Partager

Métriques

Consultations de la notice

73