Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data.
Saved in:
| Title: | Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data. |
|---|---|
| Authors: | Gnecco, Giorgio |
| Source: | Neural Computation. Mar2010, Vol. 22 Issue 3, p793-829. 37p. 1 Chart. |
| Subjects: | Hilbert space, Structural optimization, Approximation theory, Systemic memory hypothesis, Automatic hypothesis formation, Experimental design |
| Abstract: | Various regularization techniques are investigated in supervised learning from data. Theoretical features of the associated optimization problems are studied, and sparse suboptimal solutions are searched for. Rates of approximate optimization are estimated for sequences of suboptimal solutions formed by linear combinations of n-tuples of computational units, and statistical learning bounds are derived. As hypothesis sets, reproducing kernel Hilbert spaces and their subsets are considered. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Computation is the property of MIT Press 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: | Psychology and Behavioral Sciences Collection |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: pbh DbLabel: Psychology and Behavioral Sciences Collection An: 48046229 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Gnecco%2C+Giorgio%22">Gnecco, Giorgio</searchLink> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neural+Computation%22">Neural Computation</searchLink>. Mar2010, Vol. 22 Issue 3, p793-829. 37p. 1 Chart. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Hilbert+space%22">Hilbert space</searchLink><br /><searchLink fieldCode="DE" term="%22Structural+optimization%22">Structural optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Approximation+theory%22">Approximation theory</searchLink><br /><searchLink fieldCode="DE" term="%22Systemic+memory+hypothesis%22">Systemic memory hypothesis</searchLink><br /><searchLink fieldCode="DE" term="%22Automatic+hypothesis+formation%22">Automatic hypothesis formation</searchLink><br /><searchLink fieldCode="DE" term="%22Experimental+design%22">Experimental design</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Various regularization techniques are investigated in supervised learning from data. Theoretical features of the associated optimization problems are studied, and sparse suboptimal solutions are searched for. Rates of approximate optimization are estimated for sequences of suboptimal solutions formed by linear combinations of n-tuples of computational units, and statistical learning bounds are derived. As hypothesis sets, reproducing kernel Hilbert spaces and their subsets are considered. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neural Computation is the property of MIT Press 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=pbh&AN=48046229 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1162/neco.2009.05-08-786 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 37 StartPage: 793 Subjects: – SubjectFull: Hilbert space Type: general – SubjectFull: Structural optimization Type: general – SubjectFull: Approximation theory Type: general – SubjectFull: Systemic memory hypothesis Type: general – SubjectFull: Automatic hypothesis formation Type: general – SubjectFull: Experimental design Type: general Titles: – TitleFull: Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Gnecco, Giorgio IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: Mar2010 Type: published Y: 2010 Identifiers: – Type: issn-print Value: 08997667 Numbering: – Type: volume Value: 22 – Type: issue Value: 3 Titles: – TitleFull: Neural Computation Type: main |
| ResultId | 1 |
