We consider the problem of estimating filamentary structure from d-dimensional point process data. We make some connections with computational geometry and develop nonparametric methods for estimating the filaments. We show that, under weak conditions, the filaments have a simple geometric representation as the medial axis of the data distribution's support. Our methods convert an estimator of the support's boundary into an estimator of the filaments. We also find the rates of convergence of our estimators. Proofs of all results are in the supplementary material available online. © 2012 American Statistical Association.

The geometry of nonparametric filament estimation / Genovese, Christopher R.; Perone Pacifico, Marco; Verdinelli, Isabella; Wasserman, Larry. - In: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION. - ISSN 0162-1459. - 107:498(2012), pp. 788-799. [10.1080/01621459.2012.682527]

The geometry of nonparametric filament estimation

Marco Perone Pacifico;
2012

Abstract

We consider the problem of estimating filamentary structure from d-dimensional point process data. We make some connections with computational geometry and develop nonparametric methods for estimating the filaments. We show that, under weak conditions, the filaments have a simple geometric representation as the medial axis of the data distribution's support. Our methods convert an estimator of the support's boundary into an estimator of the filaments. We also find the rates of convergence of our estimators. Proofs of all results are in the supplementary material available online. © 2012 American Statistical Association.
principal curves; manifold learning; filaments; density estimation; clustering
The geometry of nonparametric filament estimation / Genovese, Christopher R.; Perone Pacifico, Marco; Verdinelli, Isabella; Wasserman, Larry. - In: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION. - ISSN 0162-1459. - 107:498(2012), pp. 788-799. [10.1080/01621459.2012.682527]
File in questo prodotto:
File Dimensione Formato  
2012_JASA.pdf

Solo gestori archivio

Tipologia: Versione dell'editore
Licenza: DRM non definito
Dimensione 1.13 MB
Formato Adobe PDF
1.13 MB Adobe PDF   Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11385/182618
Citazioni
  • Scopus 25
  • ???jsp.display-item.citation.isi??? 24
social impact