Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/98580
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Applied Mathematics | en_US |
dc.creator | Nguyen, VA | en_US |
dc.creator | Shafieezadeh-Abadeh, S | en_US |
dc.creator | Yue, MC | en_US |
dc.creator | Kuhn, D | en_US |
dc.creator | Wiesemann, W | en_US |
dc.date.accessioned | 2023-05-10T02:00:28Z | - |
dc.date.available | 2023-05-10T02:00:28Z | - |
dc.identifier.isbn | 978-1-7138-0793-3 (Print on Demand(PoD)) | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/98580 | - |
dc.description | 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 8-14 Dec 2019, Vancouver, Canada | en_US |
dc.language.iso | en | en_US |
dc.publisher | NeurIPS | en_US |
dc.rights | Copyright© (2019) by individual authors and Neural Information Processing Systems Foundation Inc. | en_US |
dc.rights | Posted with permission of the author. | en_US |
dc.title | Calculating optimistic likelihoods using (geodesically) convex optimization | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.spage | 13875 | en_US |
dc.identifier.epage | 13886 | en_US |
dc.identifier.volume | 18 | en_US |
dcterms.abstract | A 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.accessRights | open access | en_US |
dcterms.bibliographicCitation | Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019, v. 18 13875-13886 | en_US |
dcterms.issued | 2019 | - |
dc.relation.ispartofbook | Advances in Neural Information Processing Systems 32 (NeurIPS 2019) | en_US |
dc.relation.conference | Conference on Neural Information Processing Systems [NeurIPS] | en_US |
dc.description.validate | 202305 bcch | en_US |
dc.description.oa | Version of Record | en_US |
dc.identifier.FolderNumber | AMA-0255 | - |
dc.description.fundingSource | Self-funded | en_US |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 23269627 | - |
Appears in Collections: | Conference Paper |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Nguyag_Calculating_Optimistic_Likelihoods.pdf | 564.65 kB | Adobe PDF | View/Open |
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.