Publikation: End-to-End Learning for Stochastic Optimization : a Bayesian Perspective
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this analysis, we then propose new end-to-end learning algorithms for training decision maps that output solutions of empirical risk minimization and distributionally robust optimization problems, two dominant modeling paradigms in optimization under uncertainty. Numerical results for a synthetic newsvendor problem illustrate the key differences between alternative training schemes. We also investigate an economic dispatch problem based on real data to showcase the impact of the neural network architecture of the decision maps on their test performance.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
RYCHENER, Yves, Daniel KUHN, Tobias SUTTER, 2023. End-to-End Learning for Stochastic Optimization : a Bayesian Perspective. 40th International Conference on Machine Learning. Honolulu, Hawaii, 23. Juli 2023 - 29. Juli 2023. In: Proceedings of the 40th International Conference on Machine Learning. PMLR, 2023, S. 29455-29472. Proceedings of Machine Learning Research. 202. ISSN 2640-3498BibTex
@inproceedings{Rychener2023Endto-69416, year={2023}, title={End-to-End Learning for Stochastic Optimization : a Bayesian Perspective}, url={https://proceedings.mlr.press/v202/rychener23a.html}, number={202}, issn={2640-3498}, publisher={PMLR}, series={Proceedings of Machine Learning Research}, booktitle={Proceedings of the 40th International Conference on Machine Learning}, pages={29455--29472}, author={Rychener, Yves and Kuhn, Daniel and Sutter, Tobias} }
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/123456789/69416"> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/69416/1/Rychener_2-1fvomfc7v0d464.pdf"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-02-28T12:22:55Z</dcterms:available> <dc:contributor>Sutter, Tobias</dc:contributor> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/69416"/> <dcterms:abstract>We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this analysis, we then propose new end-to-end learning algorithms for training decision maps that output solutions of empirical risk minimization and distributionally robust optimization problems, two dominant modeling paradigms in optimization under uncertainty. Numerical results for a synthetic newsvendor problem illustrate the key differences between alternative training schemes. We also investigate an economic dispatch problem based on real data to showcase the impact of the neural network architecture of the decision maps on their test performance.</dcterms:abstract> <dcterms:issued>2023</dcterms:issued> <dc:creator>Kuhn, Daniel</dc:creator> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-02-28T12:22:55Z</dc:date> <dc:contributor>Kuhn, Daniel</dc:contributor> <dcterms:title>End-to-End Learning for Stochastic Optimization : a Bayesian Perspective</dcterms:title> <dc:contributor>Rychener, Yves</dc:contributor> <dc:creator>Sutter, Tobias</dc:creator> <dc:language>eng</dc:language> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:creator>Rychener, Yves</dc:creator> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/69416/1/Rychener_2-1fvomfc7v0d464.pdf"/> </rdf:Description> </rdf:RDF>