Tighter PAC-Bayes bounds through distribution-dependent priors
Saved in:
| Title: | Tighter PAC-Bayes bounds through distribution-dependent priors |
|---|---|
| Authors: | Lever, Guy1 g.lever@cs.ucl.ac.uk, Laviolette, François2, Shawe-Taylor, John1 |
| Source: | Theoretical Computer Science. Feb2013, Vol. 473, p4-28. 25p. |
| Subjects: | Mathematical bounds, Algorithms, Bayes' theorem, Stochastic matrices, Support vector machines, Mathematical regularization |
| Abstract: | Abstract: We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We use this framework to prove sharp risk bounds for stochastic exponential weights algorithms, and develop insights into controlling function class complexity in this method. In particular we consider controlling capacity with respect to the unknown geometry defined by the data-generating distribution. We also use the method to obtain new bounds for RKHS regularization schemes such as SVMs. [Copyright &y& Elsevier] |
| Copyright of Theoretical Computer Science is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 85282369 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Tighter PAC-Bayes bounds through distribution-dependent priors – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Lever%2C+Guy%22">Lever, Guy</searchLink><relatesTo>1</relatesTo><i> g.lever@cs.ucl.ac.uk</i><br /><searchLink fieldCode="AR" term="%22Laviolette%2C+François%22">Laviolette, François</searchLink><relatesTo>2</relatesTo><br /><searchLink fieldCode="AR" term="%22Shawe-Taylor%2C+John%22">Shawe-Taylor, John</searchLink><relatesTo>1</relatesTo> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Theoretical+Computer+Science%22">Theoretical Computer Science</searchLink>. Feb2013, Vol. 473, p4-28. 25p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Mathematical+bounds%22">Mathematical bounds</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Bayes'+theorem%22">Bayes' theorem</searchLink><br /><searchLink fieldCode="DE" term="%22Stochastic+matrices%22">Stochastic matrices</searchLink><br /><searchLink fieldCode="DE" term="%22Support+vector+machines%22">Support vector machines</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+regularization%22">Mathematical regularization</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Abstract: We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We use this framework to prove sharp risk bounds for stochastic exponential weights algorithms, and develop insights into controlling function class complexity in this method. In particular we consider controlling capacity with respect to the unknown geometry defined by the data-generating distribution. We also use the method to obtain new bounds for RKHS regularization schemes such as SVMs. [Copyright &y& Elsevier] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Theoretical Computer Science is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=85282369 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.tcs.2012.10.013 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 25 StartPage: 4 Subjects: – SubjectFull: Mathematical bounds Type: general – SubjectFull: Algorithms Type: general – SubjectFull: Bayes' theorem Type: general – SubjectFull: Stochastic matrices Type: general – SubjectFull: Support vector machines Type: general – SubjectFull: Mathematical regularization Type: general Titles: – TitleFull: Tighter PAC-Bayes bounds through distribution-dependent priors Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Lever, Guy – PersonEntity: Name: NameFull: Laviolette, François – PersonEntity: Name: NameFull: Shawe-Taylor, John IsPartOfRelationships: – BibEntity: Dates: – D: 18 M: 02 Text: Feb2013 Type: published Y: 2013 Identifiers: – Type: issn-print Value: 03043975 Numbering: – Type: volume Value: 473 Titles: – TitleFull: Theoretical Computer Science Type: main |
| ResultId | 1 |
