Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/98580
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Applied Mathematicsen_US
dc.creatorNguyen, VAen_US
dc.creatorShafieezadeh-Abadeh, Sen_US
dc.creatorYue, MCen_US
dc.creatorKuhn, Den_US
dc.creatorWiesemann, Wen_US
dc.date.accessioned2023-05-10T02:00:28Z-
dc.date.available2023-05-10T02:00:28Z-
dc.identifier.isbn978-1-7138-0793-3 (Print on Demand(PoD))en_US
dc.identifier.urihttp://hdl.handle.net/10397/98580-
dc.description33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 8-14 Dec 2019, Vancouver, Canadaen_US
dc.language.isoenen_US
dc.publisherNeurIPSen_US
dc.rightsCopyright© (2019) by individual authors and Neural Information Processing Systems Foundation Inc.en_US
dc.rightsPosted with permission of the author.en_US
dc.titleCalculating optimistic likelihoods using (geodesically) convex optimizationen_US
dc.typeConference Paperen_US
dc.identifier.spage13875en_US
dc.identifier.epage13886en_US
dc.identifier.volume18en_US
dcterms.abstractA fundamental problem arising in many areas of machine learning is the evaluation of the likelihood of a given observation under different nominal distributions. Frequently, these nominal distributions are themselves estimated from data, which makes them susceptible to estimation errors. We thus propose to replace each nominal distribution with an ambiguity set containing all distributions in its vicinity and to evaluate an optimistic likelihood, that is, the maximum of the likelihood over all distributions in the ambiguity set. When the proximity of distributions is quantified by the Fisher-Rao distance or the Kullback-Leibler divergence, the emerging optimistic likelihoods can be computed efficiently using either geodesic or standard convex optimization techniques. We showcase the advantages of working with optimistic likelihoods on a classification problem using synthetic as well as empirical data.en_US
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitationAdvances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019, v. 18 13875-13886en_US
dcterms.issued2019-
dc.relation.ispartofbookAdvances in Neural Information Processing Systems 32 (NeurIPS 2019)en_US
dc.relation.conferenceConference on Neural Information Processing Systems [NeurIPS]en_US
dc.description.validate202305 bcchen_US
dc.description.oaVersion of Recorden_US
dc.identifier.FolderNumberAMA-0255-
dc.description.fundingSourceSelf-fundeden_US
dc.description.pubStatusPublisheden_US
dc.identifier.OPUS23269627-
Appears in Collections:Conference Paper
Files in This Item:
File Description SizeFormat 
Nguyag_Calculating_Optimistic_Likelihoods.pdf564.65 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

Page views

31
Citations as of Nov 22, 2023

Downloads

3
Citations as of Nov 22, 2023

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.