KOPS - The Institutional Repository of the University of Konstanz

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

Cite This

Files in this item

Files Size Format View

There are no files associated with this item.

SUTTER, Tobias, Andreas KRAUSE, Daniel KUHN, 2021. Robust Generalization despite Distribution Shift via Minimum Discriminating Information. NeurIPS 2021 : 35th Conference on Neural Information Processing Systems (online), Dec 6, 2021 - Dec 14, 2021. In: RANZATO, Marc'Aurelio, ed., Alina BEYGELZIMER, ed., Yann DAUPHIN, ed. and others. Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021). San Diego, CA:Neural Information Processing Systems Foundation

@inproceedings{Sutter2021Robus-55736, title={Robust Generalization despite Distribution Shift via Minimum Discriminating Information}, url={https://proceedings.neurips.cc/paper/2021/hash/f86890095c957e9b949d11d15f0d0cd5-Abstract.html}, year={2021}, address={San Diego, CA}, publisher={Neural Information Processing Systems Foundation}, booktitle={Advances in Neural Information Processing Systems 34 pre-proceedings (NeurIPS 2021)}, editor={Ranzato, Marc'Aurelio and Beygelzimer, Alina and Dauphin, Yann}, author={Sutter, Tobias and Krause, Andreas and Kuhn, Daniel} }

<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/rdf/resource/123456789/55736"> <dc:creator>Krause, Andreas</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-12-02T12:27:08Z</dcterms:available> <dc:creator>Kuhn, Daniel</dc:creator> <dc:contributor>Kuhn, Daniel</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:issued>2021</dcterms:issued> <dc:rights>terms-of-use</dc:rights> <dc:contributor>Sutter, Tobias</dc:contributor> <dcterms:title>Robust Generalization despite Distribution Shift via Minimum Discriminating Information</dcterms:title> <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-12-02T12:27:08Z</dc:date> <dc:contributor>Krause, Andreas</dc:contributor> <dc:creator>Sutter, Tobias</dc:creator> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/55736"/> <dcterms:abstract xml:lang="eng">Training models that perform well under distribution shifts is a central challenge in machine learning. In this paper, we introduce a modeling framework where, in addition to training data, we have partial structural knowledge of the shifted test distribution. We employ the principle of minimum discriminating information to embed the available prior knowledge, and use distributionally robust optimization to account for uncertainty due to the limited samples. By leveraging large deviation results, we obtain explicit generalization bounds with respect to the unknown shifted distribution. Lastly, we demonstrate the versatility of our framework by demonstrating it on two rather distinct applications: (1) training classifiers on systematically biased data and (2) off-policy evaluation in Markov Decision Processes.</dcterms:abstract> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> <dc:language>eng</dc:language> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/36"/> </rdf:Description> </rdf:RDF>

This item appears in the following Collection(s)

Search KOPS


Browse

My Account