Gaussian Mixture Separation and Denoising on Parameterized Varieties

Lade...
Vorschaubild
Dateien
Blomenhofer_2-t3uuine700022.pdf
Blomenhofer_2-t3uuine700022.pdfGröße: 2.09 MBDownloads: 115
doctoral-thesis-appendix.zip
doctoral-thesis-appendix.zipGröße: 2.55 MBDownloads: 4
Datum
2022
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
DOI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Green
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Dissertation
Publikationsstatus
Published
Erschienen in
Zusammenfassung

This dissertation examines identifiability questions for mixtures of Gaussians: When are the mean vectors and covariance matrices of some Gaussian mixture uniquely determined by the mixture moments of a certain, fixed degree? Assuming generality of the parameters (i.e. the mean vectors and covariance matrices), the problem admits an efficient treatment by the theory of secant varieties, and the answer is determined by some combinatorial constrains between the rank (i.e. the number of Gaussians), the degree of the moments and the number of variables. For mixtures of centered Gaussians, it is shown that identifiability holds true in a range of ranks which is asymptotically optimal in the number of variables. This solves the problem for all degrees and "most" ranks. Nontrivial identifiability results can be obtained from degree 6 onwards. For mixtures of arbitrary Gaussians, it is shown with a similar argument that "most" secants of the degree-6 Gaussian moment variety are identifiable. The dissertation then derives an algorithm to compute low-rank powers-of-forms decompositions, a topic which is closely related to mixtures of centered Gaussians. This algorithm manages to recover the addends of a power sum decomposition, using semidefinite programming and conditions on the Gram spectrahedron of the second-order power sum.

The fourth chapter deals with semi-local projection towards parameterized varieties and is motivated by estimation problems in statistics. It is shown that a variant of Lasserre's hierarchy for these problems has finite convergence with an explicit degree bound. The last chapter shows a finite-convergence type result for a hierarchy of relaxations to detect spaces of singular matrices.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
510 Mathematik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690TAVEIRA BLOMENHOFER, Alexander, 2022. Gaussian Mixture Separation and Denoising on Parameterized Varieties [Dissertation]. Konstanz: University of Konstanz
BibTex
@phdthesis{TaveiraBlomenhofer2022Gauss-66207,
  year={2022},
  title={Gaussian Mixture Separation and Denoising on Parameterized Varieties},
  author={Taveira Blomenhofer, Alexander},
  address={Konstanz},
  school={Universität Konstanz}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/66207">
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/66207/5/Blomenhofer_2-t3uuine700022.pdf"/>
    <dcterms:title>Gaussian Mixture Separation and Denoising on Parameterized Varieties</dcterms:title>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/39"/>
    <dc:creator>Taveira Blomenhofer, Alexander</dc:creator>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/66207/4/doctoral-thesis-appendix.zip"/>
    <dc:language>eng</dc:language>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:abstract>This dissertation examines identifiability questions for mixtures of Gaussians: When are the mean vectors and covariance matrices of some Gaussian mixture uniquely determined by the mixture moments of a certain, fixed degree? Assuming generality of the parameters (i.e. the mean vectors and covariance matrices), the problem admits an efficient treatment by the theory of secant varieties, and the answer is determined by some combinatorial constrains between the rank (i.e. the number of Gaussians), the degree of the moments and the number of variables. For mixtures of centered Gaussians, it is shown that identifiability holds true in a range of ranks which is asymptotically optimal in the number of variables. This solves the problem for all degrees and "most" ranks. Nontrivial identifiability results can be obtained from degree 6 onwards. For mixtures of arbitrary Gaussians, it is shown with a similar argument that "most" secants of the degree-6 Gaussian moment variety are identifiable. The dissertation then derives an algorithm to compute low-rank powers-of-forms decompositions, a topic which is closely related to mixtures of centered Gaussians. This algorithm manages to recover the addends of a power sum decomposition, using semidefinite programming and conditions on the Gram spectrahedron of the second-order power sum. 

The fourth chapter deals with semi-local projection towards parameterized varieties and is motivated by estimation problems in statistics. 
It is shown that a variant of Lasserre's hierarchy for these problems has finite convergence with an explicit degree bound. The last chapter shows a finite-convergence type result for a hierarchy of relaxations to detect spaces of singular matrices.</dcterms:abstract>
    <dc:rights>terms-of-use</dc:rights>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-02-24T06:22:18Z</dc:date>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2023-02-24T06:22:18Z</dcterms:available>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/66207/4/doctoral-thesis-appendix.zip"/>
    <dc:contributor>Taveira Blomenhofer, Alexander</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/66207"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:issued>2022</dcterms:issued>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/39"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/66207/5/Blomenhofer_2-t3uuine700022.pdf"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
December 16, 2022
Hochschulschriftenvermerk
Konstanz, Univ., Diss., 2022
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Ja
Begutachtet
Link zu Forschungsdaten
Beschreibung der Forschungsdaten
Appendix mit Code und Daten zu numerischen Experimenten.
Diese Publikation teilen