Nonhomogeneous Euclidean first-passage percolation and distance learning
- Autores
- Groisman, Pablo Jose; Jonckheere, Matthieu Thimothy Samson; Sapienza, Facundo
- Año de publicación
- 2022
- Idioma
- inglés
- Tipo de recurso
- artículo
- Estado
- versión publicada
- Descripción
- Consider an i.i.d. sample from an unknown density function supported on an unknown manifold embedded in a high dimensional Euclidean space. We tackle the problem of learning a distance between points, able to capture both the geometry of the manifold and the underlying density. We define such a sample distance and prove the convergence, as the sample size goes to infinity, to a macroscopic one that we call Fermat distance as it minimizes a path functional, resembling Fermat principle in optics. The proof boils down to the study of geodesics in Euclidean first-passage percolation for nonhomogeneous Poisson point processes.
Fil: Groisman, Pablo Jose. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigaciones Matemáticas "Luis A. Santaló". Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigaciones Matemáticas "Luis A. Santaló"; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Cálculo; Argentina
Fil: Jonckheere, Matthieu Thimothy Samson. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Calculo. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Calculo; Argentina
Fil: Sapienza, Facundo. No especifíca; - Materia
-
DISTANCE LEARNING
EUCLIDEAN FIRST-PASSAGE PERCOLATION
NONHOMOGENEOUS POINT PROCESSES - Nivel de accesibilidad
- acceso abierto
- Condiciones de uso
- https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
- Repositorio
- Institución
- Consejo Nacional de Investigaciones Científicas y Técnicas
- OAI Identificador
- oai:ri.conicet.gov.ar:11336/170790
Ver los metadatos del registro completo
id |
CONICETDig_3217fd1eb0b3a978c9d9209783382f60 |
---|---|
oai_identifier_str |
oai:ri.conicet.gov.ar:11336/170790 |
network_acronym_str |
CONICETDig |
repository_id_str |
3498 |
network_name_str |
CONICET Digital (CONICET) |
spelling |
Nonhomogeneous Euclidean first-passage percolation and distance learningGroisman, Pablo JoseJonckheere, Matthieu Thimothy SamsonSapienza, FacundoDISTANCE LEARNINGEUCLIDEAN FIRST-PASSAGE PERCOLATIONNONHOMOGENEOUS POINT PROCESSEShttps://purl.org/becyt/ford/1.1https://purl.org/becyt/ford/1Consider an i.i.d. sample from an unknown density function supported on an unknown manifold embedded in a high dimensional Euclidean space. We tackle the problem of learning a distance between points, able to capture both the geometry of the manifold and the underlying density. We define such a sample distance and prove the convergence, as the sample size goes to infinity, to a macroscopic one that we call Fermat distance as it minimizes a path functional, resembling Fermat principle in optics. The proof boils down to the study of geodesics in Euclidean first-passage percolation for nonhomogeneous Poisson point processes.Fil: Groisman, Pablo Jose. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigaciones Matemáticas "Luis A. Santaló". Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigaciones Matemáticas "Luis A. Santaló"; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Cálculo; ArgentinaFil: Jonckheere, Matthieu Thimothy Samson. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Calculo. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Calculo; ArgentinaFil: Sapienza, Facundo. No especifíca;Institute of Mathematical Statistics2022-02info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/170790Groisman, Pablo Jose; Jonckheere, Matthieu Thimothy Samson; Sapienza, Facundo; Nonhomogeneous Euclidean first-passage percolation and distance learning; Institute of Mathematical Statistics; Bernoulli - Mathematical Statistics And Probability; 28; 1; 2-2022; 255-2761350-72651573-9759CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://projecteuclid.org/journals/bernoulli/volume-28/issue-1/Nonhomogeneous-Euclidean-first-passage-percolation-and-distance-learning/10.3150/21-BEJ1341.shortinfo:eu-repo/semantics/altIdentifier/doi/10.3150/21-BEJ1341info:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/1810.09398info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:34:49Zoai:ri.conicet.gov.ar:11336/170790instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:34:49.722CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse |
dc.title.none.fl_str_mv |
Nonhomogeneous Euclidean first-passage percolation and distance learning |
title |
Nonhomogeneous Euclidean first-passage percolation and distance learning |
spellingShingle |
Nonhomogeneous Euclidean first-passage percolation and distance learning Groisman, Pablo Jose DISTANCE LEARNING EUCLIDEAN FIRST-PASSAGE PERCOLATION NONHOMOGENEOUS POINT PROCESSES |
title_short |
Nonhomogeneous Euclidean first-passage percolation and distance learning |
title_full |
Nonhomogeneous Euclidean first-passage percolation and distance learning |
title_fullStr |
Nonhomogeneous Euclidean first-passage percolation and distance learning |
title_full_unstemmed |
Nonhomogeneous Euclidean first-passage percolation and distance learning |
title_sort |
Nonhomogeneous Euclidean first-passage percolation and distance learning |
dc.creator.none.fl_str_mv |
Groisman, Pablo Jose Jonckheere, Matthieu Thimothy Samson Sapienza, Facundo |
author |
Groisman, Pablo Jose |
author_facet |
Groisman, Pablo Jose Jonckheere, Matthieu Thimothy Samson Sapienza, Facundo |
author_role |
author |
author2 |
Jonckheere, Matthieu Thimothy Samson Sapienza, Facundo |
author2_role |
author author |
dc.subject.none.fl_str_mv |
DISTANCE LEARNING EUCLIDEAN FIRST-PASSAGE PERCOLATION NONHOMOGENEOUS POINT PROCESSES |
topic |
DISTANCE LEARNING EUCLIDEAN FIRST-PASSAGE PERCOLATION NONHOMOGENEOUS POINT PROCESSES |
purl_subject.fl_str_mv |
https://purl.org/becyt/ford/1.1 https://purl.org/becyt/ford/1 |
dc.description.none.fl_txt_mv |
Consider an i.i.d. sample from an unknown density function supported on an unknown manifold embedded in a high dimensional Euclidean space. We tackle the problem of learning a distance between points, able to capture both the geometry of the manifold and the underlying density. We define such a sample distance and prove the convergence, as the sample size goes to infinity, to a macroscopic one that we call Fermat distance as it minimizes a path functional, resembling Fermat principle in optics. The proof boils down to the study of geodesics in Euclidean first-passage percolation for nonhomogeneous Poisson point processes. Fil: Groisman, Pablo Jose. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigaciones Matemáticas "Luis A. Santaló". Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigaciones Matemáticas "Luis A. Santaló"; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Cálculo; Argentina Fil: Jonckheere, Matthieu Thimothy Samson. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Calculo. - Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Calculo; Argentina Fil: Sapienza, Facundo. No especifíca; |
description |
Consider an i.i.d. sample from an unknown density function supported on an unknown manifold embedded in a high dimensional Euclidean space. We tackle the problem of learning a distance between points, able to capture both the geometry of the manifold and the underlying density. We define such a sample distance and prove the convergence, as the sample size goes to infinity, to a macroscopic one that we call Fermat distance as it minimizes a path functional, resembling Fermat principle in optics. The proof boils down to the study of geodesics in Euclidean first-passage percolation for nonhomogeneous Poisson point processes. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-02 |
dc.type.none.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://purl.org/coar/resource_type/c_6501 info:ar-repo/semantics/articulo |
format |
article |
status_str |
publishedVersion |
dc.identifier.none.fl_str_mv |
http://hdl.handle.net/11336/170790 Groisman, Pablo Jose; Jonckheere, Matthieu Thimothy Samson; Sapienza, Facundo; Nonhomogeneous Euclidean first-passage percolation and distance learning; Institute of Mathematical Statistics; Bernoulli - Mathematical Statistics And Probability; 28; 1; 2-2022; 255-276 1350-7265 1573-9759 CONICET Digital CONICET |
url |
http://hdl.handle.net/11336/170790 |
identifier_str_mv |
Groisman, Pablo Jose; Jonckheere, Matthieu Thimothy Samson; Sapienza, Facundo; Nonhomogeneous Euclidean first-passage percolation and distance learning; Institute of Mathematical Statistics; Bernoulli - Mathematical Statistics And Probability; 28; 1; 2-2022; 255-276 1350-7265 1573-9759 CONICET Digital CONICET |
dc.language.none.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
info:eu-repo/semantics/altIdentifier/url/https://projecteuclid.org/journals/bernoulli/volume-28/issue-1/Nonhomogeneous-Euclidean-first-passage-percolation-and-distance-learning/10.3150/21-BEJ1341.short info:eu-repo/semantics/altIdentifier/doi/10.3150/21-BEJ1341 info:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/1810.09398 |
dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ |
eu_rights_str_mv |
openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ |
dc.format.none.fl_str_mv |
application/pdf application/pdf |
dc.publisher.none.fl_str_mv |
Institute of Mathematical Statistics |
publisher.none.fl_str_mv |
Institute of Mathematical Statistics |
dc.source.none.fl_str_mv |
reponame:CONICET Digital (CONICET) instname:Consejo Nacional de Investigaciones Científicas y Técnicas |
reponame_str |
CONICET Digital (CONICET) |
collection |
CONICET Digital (CONICET) |
instname_str |
Consejo Nacional de Investigaciones Científicas y Técnicas |
repository.name.fl_str_mv |
CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas |
repository.mail.fl_str_mv |
dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar |
_version_ |
1844614365213360128 |
score |
13.070432 |