Hypotheses testing on infinite random graphs
Type de document :
Communication dans un congrès avec actes
Titre :
Hypotheses testing on infinite random graphs
Auteur(s) :
Titre de la manifestation scientifique :
ALT 2017 - 28th International Conference on Algorithmic Learning Theory
Ville :
kyoto
Pays :
Japon
Date de début de la manifestation scientifique :
2017-10-15
Discipline(s) HAL :
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Théorie [stat.TH]
Statistiques [stat]/Théorie [stat.TH]
Résumé en anglais : [en]
Drawing on some recent results that provide the formalism necessary to definite stationarityfor infinite random graphs, this paper initiates the study of statistical and learning questionspertaining to these objects. ...
Lire la suite >Drawing on some recent results that provide the formalism necessary to definite stationarityfor infinite random graphs, this paper initiates the study of statistical and learning questionspertaining to these objects. Specifically, a criterion for the existence of a consistent testfor 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.Lire moins >
Lire la suite >Drawing on some recent results that provide the formalism necessary to definite stationarityfor infinite random graphs, this paper initiates the study of statistical and learning questionspertaining to these objects. Specifically, a criterion for the existence of a consistent testfor 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.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- http://arxiv.org/pdf/1708.03131
- Accès libre
- Accéder au document
- 1708.03131
- Accès libre
- Accéder au document