A Kernel for Multi-Parameter Persistent Homology

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

Publikation: KonferenzbeitragPosterForschung

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.
Originalspracheenglisch
PublikationsstatusUnveröffentlicht - 2018

Fingerprint

Learning systems

Schlagwörter

    Dies zitieren

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

    2018.

    Publikation: KonferenzbeitragPosterForschung

    Corbet, René ; Fugacci, Ulderico ; Kerber, Michael ; Landi, Claudia ; Wang, Bei. / A Kernel for Multi-Parameter Persistent Homology.
    @conference{d079627fe4c64d5ea4de7ad861f1c7f0,
    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",

    }

    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 - Poster

    ER -