File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Scopus: eid_2-s2.0-85090178488
- WOS: WOS:000535866905058
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Calculating optimistic likelihoods using (geodesically) convex optimization
Title | Calculating optimistic likelihoods using (geodesically) convex optimization |
---|---|
Authors | |
Issue Date | 2019 |
Citation | Advances in Neural Information Processing Systems, 2019, v. 32 How to Cite? |
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. |
Persistent Identifier | http://hdl.handle.net/10722/313629 |
ISSN | 2020 SCImago Journal Rankings: 1.399 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nguyen, Viet Anh | - |
dc.contributor.author | Shafieezadeh-Abadeh, Soroosh | - |
dc.contributor.author | Yue, Man Chung | - |
dc.contributor.author | Kuhn, Daniel | - |
dc.contributor.author | Wiesemann, Wolfram | - |
dc.date.accessioned | 2022-06-23T01:18:48Z | - |
dc.date.available | 2022-06-23T01:18:48Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Advances in Neural Information Processing Systems, 2019, v. 32 | - |
dc.identifier.issn | 1049-5258 | - |
dc.identifier.uri | http://hdl.handle.net/10722/313629 | - |
dc.description.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. | - |
dc.language | eng | - |
dc.relation.ispartof | Advances in Neural Information Processing Systems | - |
dc.title | Calculating optimistic likelihoods using (geodesically) convex optimization | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.scopus | eid_2-s2.0-85090178488 | - |
dc.identifier.volume | 32 | - |
dc.identifier.isi | WOS:000535866905058 | - |