Aufgrund von Vorbereitungen auf eine neue Version von KOPS, können kommenden Montag und Dienstag keine Publikationen eingereicht werden. (Due to preparations for a new version of KOPS, no publications can be submitted next Monday and Tuesday.)

Risk Bounds for Reservoir Computing

Cite This

Files in this item

Checksum: MD5:fd5473bf05bc06043a89e114c778a2d6

GONON, Lukas, Lyudmila GRIGORYEVA, Juan-Pablo ORTEGA, 2020. Risk Bounds for Reservoir Computing. In: Journal of Machine Learning Research (JMLR). Microtome Publishing. 21, 240. ISSN 1532-4435. eISSN 1533-7928

@article{Gonon2020Bound-52899, title={Risk Bounds for Reservoir Computing}, url={}, year={2020}, volume={21}, issn={1532-4435}, journal={Journal of Machine Learning Research (JMLR)}, author={Gonon, Lukas and Grigoryeva, Lyudmila and Ortega, Juan-Pablo}, note={Article Number: 240} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <dc:contributor>Gonon, Lukas</dc:contributor> <dspace:hasBitstream rdf:resource=""/> <dc:creator>Grigoryeva, Lyudmila</dc:creator> <dcterms:available rdf:datatype="">2021-02-18T10:24:29Z</dcterms:available> <dcterms:abstract xml:lang="eng">We analyze the practices of reservoir computing in the framework of statistical learning theory. In particular, we derive finite sample upper bounds for the generalization error committed by specific families of reservoir computing systems when processing discrete-time inputs under various hypotheses on their dependence structure. Non-asymptotic bounds are explicitly written down in terms of the multivariate Rademacher complexities of the reservoir systems and the weak dependence structure of the signals that are being handled. This allows, in particular, to determine the minimal number of observations needed in order to guarantee a prescribed estimation accuracy with high probability for a given reservoir family. At the same time, the asymptotic behavior of the devised bounds guarantees the consistency of the empirical risk minimization procedure for various hypothesis classes of reservoir functionals.</dcterms:abstract> <dc:creator>Gonon, Lukas</dc:creator> <dc:contributor>Grigoryeva, Lyudmila</dc:contributor> <dc:rights>Attribution 4.0 International</dc:rights> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:contributor>Ortega, Juan-Pablo</dc:contributor> <dspace:isPartOfCollection rdf:resource=""/> <dcterms:hasPart rdf:resource=""/> <dcterms:title>Risk Bounds for Reservoir Computing</dcterms:title> <dcterms:issued>2020</dcterms:issued> <bibo:uri rdf:resource=""/> <dcterms:isPartOf rdf:resource=""/> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dcterms:rights rdf:resource=""/> <dc:creator>Ortega, Juan-Pablo</dc:creator> <dc:date rdf:datatype="">2021-02-18T10:24:29Z</dc:date> <dc:language>eng</dc:language> </rdf:Description> </rdf:RDF>

Downloads since Feb 18, 2021 (Information about access statistics)

Gonon_2-1bk1kceuhte259.pdf 76

This item appears in the following Collection(s)

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International

Search KOPS


My Account