Hypotheses testing on infinite random graphs

Daniil Ryabko
Proceedings of the 28th International Conference on Algorithmic Learning Theory, PMLR 76:400-411, 2017.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v76-ryabko17b, title = {Hypotheses testing on infinite random graphs}, author = {Ryabko, Daniil}, booktitle = {Proceedings of the 28th International Conference on Algorithmic Learning Theory}, pages = {400--411}, year = {2017}, editor = {Hanneke, Steve and Reyzin, Lev}, volume = {76}, series = {Proceedings of Machine Learning Research}, month = {15--17 Oct}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v76/ryabko17b/ryabko17b.pdf}, url = {https://proceedings.mlr.press/v76/ryabko17b.html}, 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.} }
Endnote
%0 Conference Paper %T Hypotheses testing on infinite random graphs %A Daniil Ryabko %B Proceedings of the 28th International Conference on Algorithmic Learning Theory %C Proceedings of Machine Learning Research %D 2017 %E Steve Hanneke %E Lev Reyzin %F pmlr-v76-ryabko17b %I PMLR %P 400--411 %U https://proceedings.mlr.press/v76/ryabko17b.html %V 76 %X 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.
APA
Ryabko, D.. (2017). Hypotheses testing on infinite random graphs. Proceedings of the 28th International Conference on Algorithmic Learning Theory, in Proceedings of Machine Learning Research 76:400-411 Available from https://proceedings.mlr.press/v76/ryabko17b.html.

Related Material