Generalized Maximum Entropy Estimation

Sutter, Tobias; Sutter, David; Esfahani, Peyman Mohajerin; Lygeros, John

Generalized Maximum Entropy Estimation

Dateien

Sutter_2-1svqydo8rxhan3.pdfGröße: 562.66 KBDownloads: 97

Datum

2019

Autor:innen

Sutter, Tobias

Sutter, David

Esfahani, Peyman Mohajerin

Lygeros, John

URI (zitierfähiger Link)

http://nbn-resolving.de/urn:nbn:de:bsz:352-2-1svqydo8rxhan3

Link zur Lizenz

Urheberrechtlich geschützt

Open Access-Veröffentlichung

Open Access Hybrid

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

Journal of Machine Learning Research. Microtome Publishing. 2019, 20, 138. ISSN 1532-4435. eISSN 1533-7928

Zusammenfassung

We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise. Based on duality of convex programming, we present a novel approximation scheme using a smoothed fast gradient method that is equipped with explicit bounds on the approximation error. We further demonstrate how the presented scheme can be used for approximating the chemical master equation through the zero-information moment closure method, and for an approximate dynamic programming approach in the context of constrained Markov decision processes with uncountable state and action spaces.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Entropy maximization, convex optimization, relative entropy minimization, fast gradient method, approximate dynamic programming

Zitieren

ISO 690

SUTTER, Tobias, David SUTTER, Peyman Mohajerin ESFAHANI, John LYGEROS, 2019. Generalized Maximum Entropy Estimation. In: Journal of Machine Learning Research. Microtome Publishing. 2019, 20, 138. ISSN 1532-4435. eISSN 1533-7928

BibTex

@article{Sutter2019Gener-55731,
  year={2019},
  title={Generalized Maximum Entropy Estimation},
  url={https://jmlr.org/papers/v20/17-486.html},
  volume={20},
  issn={1532-4435},
  journal={Journal of Machine Learning Research},
  author={Sutter, Tobias and Sutter, David and Esfahani, Peyman Mohajerin and Lygeros, John},
  note={Article Number: 138}
}

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/123456789/55731">
    <dc:creator>Sutter, David</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-12-02T11:58:34Z</dc:date>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/55731/1/Sutter_2-1svqydo8rxhan3.pdf"/>
    <dc:contributor>Sutter, David</dc:contributor>
    <dc:creator>Lygeros, John</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:creator>Esfahani, Peyman Mohajerin</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/55731"/>
    <dcterms:issued>2019</dcterms:issued>
    <dcterms:abstract xml:lang="eng">We consider the problem of estimating a probability distribution that maximizes the entropy while satisfying a finite number of moment constraints, possibly corrupted by noise. Based on duality of convex programming, we present a novel approximation scheme using a smoothed fast gradient method that is equipped with explicit bounds on the approximation error. We further demonstrate how the presented scheme can be used for approximating the chemical master equation through the zero-information moment closure method, and for an approximate dynamic programming approach in the context of constrained Markov decision processes with uncountable state and action spaces.</dcterms:abstract>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-12-02T11:58:34Z</dcterms:available>
    <dc:creator>Sutter, Tobias</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/55731/1/Sutter_2-1svqydo8rxhan3.pdf"/>
    <dc:contributor>Sutter, Tobias</dc:contributor>
    <dcterms:title>Generalized Maximum Entropy Estimation</dcterms:title>
    <dc:language>eng</dc:language>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Esfahani, Peyman Mohajerin</dc:contributor>
    <dc:contributor>Lygeros, John</dc:contributor>
  </rdf:Description>
</rdf:RDF>

URL der Originalveröffentl.

https://jmlr.org/papers/v20/17-486.html

Prüfdatum der URL

2021-12-02

Universitätsbibliographie

Nein

Begutachtet

Ja