A Generalization Error Bound for Multi-class Domain Generalization
Domain generalization is the problem of assigning labels to an unlabeled data set, given several similar data sets for which labels have been provided. Despite considerable interest in this problem over the last decade, there has been no theoretical analysis in the setting of multi-class classificat...
Saved in:
| Main Authors | , , , , , |
|---|---|
| Format | Journal Article |
| Language | English |
| Published |
24.05.2019
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Domain generalization is the problem of assigning labels to an unlabeled data
set, given several similar data sets for which labels have been provided.
Despite considerable interest in this problem over the last decade, there has
been no theoretical analysis in the setting of multi-class classification. In
this work, we study a kernel-based learning algorithm and establish a
generalization error bound that scales logarithmically in the number of
classes, matching state-of-the-art bounds for multi-class classification in the
conventional learning setting. We also demonstrate empirically that the
proposed algorithm achieves significant performance gains compared to a pooling
strategy. |
|---|---|
| AbstractList | Domain generalization is the problem of assigning labels to an unlabeled data
set, given several similar data sets for which labels have been provided.
Despite considerable interest in this problem over the last decade, there has
been no theoretical analysis in the setting of multi-class classification. In
this work, we study a kernel-based learning algorithm and establish a
generalization error bound that scales logarithmically in the number of
classes, matching state-of-the-art bounds for multi-class classification in the
conventional learning setting. We also demonstrate empirically that the
proposed algorithm achieves significant performance gains compared to a pooling
strategy. |
| Author | Sharma, Srinagesh Dogan, Urun Cutler, James W Lei, Yunwen Deshmukh, Aniket Anand Scott, Clayton |
| Author_xml | – sequence: 1 givenname: Aniket Anand surname: Deshmukh fullname: Deshmukh, Aniket Anand – sequence: 2 givenname: Yunwen surname: Lei fullname: Lei, Yunwen – sequence: 3 givenname: Srinagesh surname: Sharma fullname: Sharma, Srinagesh – sequence: 4 givenname: Urun surname: Dogan fullname: Dogan, Urun – sequence: 5 givenname: James W surname: Cutler fullname: Cutler, James W – sequence: 6 givenname: Clayton surname: Scott fullname: Scott, Clayton |
| BackLink | https://doi.org/10.48550/arXiv.1905.10392$$DView paper in arXiv |
| BookMark | eNpdj8tuwjAURL1oF0D7AazwDyTYTmJyl0B5SVRs2EfXL8lSsCsHqpavJ0BXXc3RSDPSGZKXEIMlZMxZXtZVxaaYfvx3zoFVOWcFiAFZzOnGBpuw9Vc8-xjoKqWY6CJegqGup89Le_aZbrHr6Ec8oQ__Fm_k1WHb2fe_HJHjenVcbrP9YbNbzvcZypnIhOAGXAkFBy0NWi2dsqCNqk3fgy6FMVwDoipdBQJlj5pzpmujpBJYjMjkefuQaL6SP2H6be4yzUOmuAGTtUe7 |
| ContentType | Journal Article |
| Copyright | http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| Copyright_xml | – notice: http://arxiv.org/licenses/nonexclusive-distrib/1.0 |
| DBID | AKY EPD GOX |
| DOI | 10.48550/arxiv.1905.10392 |
| DatabaseName | arXiv Computer Science arXiv Statistics arXiv.org |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: GOX name: arXiv.org url: http://arxiv.org/find sourceTypes: Open Access Repository |
| DeliveryMethod | fulltext_linktorsrc |
| ExternalDocumentID | 1905_10392 |
| GroupedDBID | AKY EPD GOX |
| ID | FETCH-LOGICAL-a672-221d9f49319c6daec6fbe9cdb8dd9f9c42dd1c9aab4f592a69aac110c8db6b2a3 |
| IEDL.DBID | GOX |
| IngestDate | Mon Jan 08 05:43:56 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a672-221d9f49319c6daec6fbe9cdb8dd9f9c42dd1c9aab4f592a69aac110c8db6b2a3 |
| OpenAccessLink | https://arxiv.org/abs/1905.10392 |
| ParticipantIDs | arxiv_primary_1905_10392 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-05-24 |
| PublicationDateYYYYMMDD | 2019-05-24 |
| PublicationDate_xml | – month: 05 year: 2019 text: 2019-05-24 day: 24 |
| PublicationDecade | 2010 |
| PublicationYear | 2019 |
| Score | 1.7359507 |
| SecondaryResourceType | preprint |
| Snippet | Domain generalization is the problem of assigning labels to an unlabeled data
set, given several similar data sets for which labels have been provided.
Despite... |
| SourceID | arxiv |
| SourceType | Open Access Repository |
| SubjectTerms | Computer Science - Learning Statistics - Machine Learning |
| Title | A Generalization Error Bound for Multi-class Domain Generalization |
| URI | https://arxiv.org/abs/1905.10392 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwdV1LSwMxEA61Jy-iqNQnOXgNNrPZ7ObYamsR1EuFvZVMHuBBK2sVf76T7IoieAt5QSZhvm9IvgljF6WvfYG1FFDFIJSVRiARUQFSeSIcOC5sUiPf3evFo7ptymbA-LcWxrafTx9dfmB8uyS0KpMs3JCT3QJIT7ZuHprucjKn4ur7__QjjpmrfoHEfJft9OyOT7rt2GOD8LLPphPeJ3fuNY981rbrlk_Tj0acSCPPKljhEpHl1-tnCtb_jDhgy_lsebUQ_dcFwuoKBID0JipD59tpb4PTEYNxHmtP9cYp8F46Yy2qWBqwmoqOgNjVHjWCLQ7ZkKL_MGK8CCXNBaaGOFYeCZ1l5XwZi4o8g0J9xEZ5wavXLjvFKtlilW1x_H_TCdsm5DfpGhzUKRtu2vdwRui6wfNs4i_r03rZ |
| link.rule.ids | 228,230,783,888 |
| linkProvider | Cornell University |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=A+Generalization+Error+Bound+for+Multi-class+Domain+Generalization&rft.au=Deshmukh%2C+Aniket+Anand&rft.au=Lei%2C+Yunwen&rft.au=Sharma%2C+Srinagesh&rft.au=Dogan%2C+Urun&rft.date=2019-05-24&rft_id=info:doi/10.48550%2Farxiv.1905.10392&rft.externalDocID=1905_10392 |