A Kernel for Multi-Parameter Persistent Homology

René Corbet, Ulderico Fugacci, Michael Kerber, Claudia Landi, Bei Wang

Research output: Contribution to conferenceAbstractResearchpeer-review

Abstract

Topological data analysis and its main method, persistent homology, provide a toolkit for computing topological information of high-dimensional and noisy data sets. Kernels for one-parameter persistent homology have been established to connect persistent homology with machine learning techniques. We contribute a kernel construction for multi-parameter persistence by integrating a one-parameter kernel weighted along straight lines. We prove that our kernel is stable and efficiently computable, which establishes a theoretical connection between topological data analysis and machine learning for multivariate data analysis.
Original languageEnglish
Publication statusUnpublished - 2018
Event34th International Symposium on Computational Geometry, SoCG 2018 - Budapest, Hungary
Duration: 11 Jun 201814 Jun 2018

Conference

Conference34th International Symposium on Computational Geometry, SoCG 2018
CountryHungary
CityBudapest
Period11/06/1814/06/18

Fingerprint

Learning systems

Keywords

  • cs.LG
  • cs.CG
  • math.AT
  • stat.ML

Cite this

Corbet, R., Fugacci, U., Kerber, M., Landi, C., & Wang, B. (2018). A Kernel for Multi-Parameter Persistent Homology. Abstract from 34th International Symposium on Computational Geometry, SoCG 2018, Budapest, Hungary.

A Kernel for Multi-Parameter Persistent Homology. / Corbet, René; Fugacci, Ulderico; Kerber, Michael; Landi, Claudia; Wang, Bei.

2018. Abstract from 34th International Symposium on Computational Geometry, SoCG 2018, Budapest, Hungary.

Research output: Contribution to conferenceAbstractResearchpeer-review

Corbet, R, Fugacci, U, Kerber, M, Landi, C & Wang, B 2018, 'A Kernel for Multi-Parameter Persistent Homology' 34th International Symposium on Computational Geometry, SoCG 2018, Budapest, Hungary, 11/06/18 - 14/06/18, .
Corbet R, Fugacci U, Kerber M, Landi C, Wang B. A Kernel for Multi-Parameter Persistent Homology. 2018. Abstract from 34th International Symposium on Computational Geometry, SoCG 2018, Budapest, Hungary.
Corbet, René ; Fugacci, Ulderico ; Kerber, Michael ; Landi, Claudia ; Wang, Bei. / A Kernel for Multi-Parameter Persistent Homology. Abstract from 34th International Symposium on Computational Geometry, SoCG 2018, Budapest, Hungary.
@conference{00f9794510624a0ca77b08b376cec774,
title = "A Kernel for Multi-Parameter Persistent Homology",
abstract = "Topological data analysis and its main method, persistent homology, provide a toolkit for computing topological information of high-dimensional and noisy data sets. Kernels for one-parameter persistent homology have been established to connect persistent homology with machine learning techniques. We contribute a kernel construction for multi-parameter persistence by integrating a one-parameter kernel weighted along straight lines. We prove that our kernel is stable and efficiently computable, which establishes a theoretical connection between topological data analysis and machine learning for multivariate data analysis.",
keywords = "cs.LG, cs.CG, math.AT, stat.ML",
author = "Ren{\'e} Corbet and Ulderico Fugacci and Michael Kerber and Claudia Landi and Bei Wang",
year = "2018",
language = "English",
note = "34th International Symposium on Computational Geometry, SoCG 2018 ; Conference date: 11-06-2018 Through 14-06-2018",

}

TY - CONF

T1 - A Kernel for Multi-Parameter Persistent Homology

AU - Corbet, René

AU - Fugacci, Ulderico

AU - Kerber, Michael

AU - Landi, Claudia

AU - Wang, Bei

PY - 2018

Y1 - 2018

N2 - Topological data analysis and its main method, persistent homology, provide a toolkit for computing topological information of high-dimensional and noisy data sets. Kernels for one-parameter persistent homology have been established to connect persistent homology with machine learning techniques. We contribute a kernel construction for multi-parameter persistence by integrating a one-parameter kernel weighted along straight lines. We prove that our kernel is stable and efficiently computable, which establishes a theoretical connection between topological data analysis and machine learning for multivariate data analysis.

AB - Topological data analysis and its main method, persistent homology, provide a toolkit for computing topological information of high-dimensional and noisy data sets. Kernels for one-parameter persistent homology have been established to connect persistent homology with machine learning techniques. We contribute a kernel construction for multi-parameter persistence by integrating a one-parameter kernel weighted along straight lines. We prove that our kernel is stable and efficiently computable, which establishes a theoretical connection between topological data analysis and machine learning for multivariate data analysis.

KW - cs.LG

KW - cs.CG

KW - math.AT

KW - stat.ML

M3 - Abstract

ER -