COPYRIGHT YEAR

2008

AUTHORS

Jing Hu, Jong-Shi Pang, Gautam Kunapuli, Kristin P. Bennett

TITLE

Bilevel Optimization and Machine Learning

ABSTRACT

We examine the interplay of optimization and machine learning. Great progress has been made in machine learning by cleverly reducing machine learning problems to convex optimization problems with one or more hyper-parameters. The availability of powerful convex-programming theory and algorithms has enabled a flood of new research in machine learning models and methods. But many of the steps necessary for successful machine learning models fall outside of the convex machine learning paradigm. Thus we now propose framing machine learning problems as Stackelberg games. The resulting bilevel optimization problem allows for efficient systematic search of large numbers of hyper-parameters. We discuss recent progress in solving these bilevel problems and the many interesting optimization challenges that remain. Finally, we investigate the intriguing possibility of novel machine learning models enabled by bilevel programming.

Related objects

How to use: Click on a object to move its position. Double click to open its homepage. Right click to preview its contents.

Download the RDF metadata as:   json-ld nt turtle xml License info


28 TRIPLES      24 PREDICATES      25 URIs      13 LITERALS

Subject Predicate Object
1 book-chapters:36891ee775c11bb53fcc878a8b66d22d sg:abstract Abstract We examine the interplay of optimization and machine learning. Great progress has been made in machine learning by cleverly reducing machine learning problems to convex optimization problems with one or more hyper-parameters. The availability of powerful convex-programming theory and algorithms has enabled a flood of new research in machine learning models and methods. But many of the steps necessary for successful machine learning models fall outside of the convex machine learning paradigm. Thus we now propose framing machine learning problems as Stackelberg games. The resulting bilevel optimization problem allows for efficient systematic search of large numbers of hyper-parameters. We discuss recent progress in solving these bilevel problems and the many interesting optimization challenges that remain. Finally, we investigate the intriguing possibility of novel machine learning models enabled by bilevel programming.
2 sg:abstractRights OpenAccess
3 sg:bibliographyRights Restricted
4 sg:bodyHtmlRights Restricted
5 sg:bodyPdfRights Restricted
6 sg:copyrightHolder Springer-Verlag Berlin Heidelberg
7 sg:copyrightYear 2008
8 sg:ddsId Chap2
9 sg:doi 10.1007/978-3-540-68860-0_2
10 sg:esmRights OpenAccess
11 sg:hasBook books:53815bb76e34bd112a274aca71b9d27e
12 sg:hasContributingOrganization grid-institutes:grid.33647.35
13 grid-institutes:grid.35403.31
14 sg:hasContribution contributions:42ebb3901327c0adf31a9ac976036055
15 contributions:91f2e84c71eaa8b24677a40adc2b0c01
16 contributions:d2f4052aeecb160cffcc4d44331e25b4
17 contributions:e8903b4ad6a4884b297e8c4c7135e871
18 sg:language En
19 sg:license http://scigraph.springernature.com/explorer/license/
20 sg:metadataRights OpenAccess
21 sg:pageFirst 25
22 sg:pageLast 47
23 sg:scigraphId 36891ee775c11bb53fcc878a8b66d22d
24 sg:title Bilevel Optimization and Machine Learning
25 sg:webpage https://link.springer.com/10.1007/978-3-540-68860-0_2
26 rdf:type sg:BookChapter
27 rdfs:label BookChapter: Bilevel Optimization and Machine Learning
28 owl:sameAs http://lod.springer.com/data/bookchapter/978-3-540-68860-0_2
HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular JSON format for linked data.

curl -H 'Accept: application/ld+json' 'http://scigraph.springernature.com/things/book-chapters/36891ee775c11bb53fcc878a8b66d22d'

N-Triples is a line-based linked data format ideal for batch operations .

curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/book-chapters/36891ee775c11bb53fcc878a8b66d22d'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/book-chapters/36891ee775c11bb53fcc878a8b66d22d'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/book-chapters/36891ee775c11bb53fcc878a8b66d22d'






Preview window. Press ESC to close (or click here)


...