Hypotheses testing on infinite random graphs
Document type :
Communication dans un congrès avec actes
Title :
Hypotheses testing on infinite random graphs
Author(s) :
Conference title :
ALT 2017 - 28th International Conference on Algorithmic Learning Theory
City :
kyoto
Country :
Japon
Start date of the conference :
2017-10-15
HAL domain(s) :
Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Théorie [stat.TH]
Statistiques [stat]/Théorie [stat.TH]
English abstract : [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. ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- http://arxiv.org/pdf/1708.03131
- Open access
- Access the document
- 1708.03131
- Open access
- Access the document