PUBLICATION DATE

2010-07-16

TITLE

Machine learning problems from optimization perspective

ISSUE

6

VOLUME

61

ISSN (print)

0020-580X

ISSN (electronic)

1476-9352

ABSTRACT

Both optimization and learning play important roles in a system for intelligent tasks. On one hand, we introduce three types of optimization tasks studied in the machine learning literature, corresponding to the three levels of inverse problems in an intelligent system. Also, we discuss three major roles of convexity in machine learning, either directly towards a convex programming or approximately transferring a difficult problem into a tractable one in help of local convexity and convex duality. No doubly, a good optimization algorithm takes an essential role in a learning process and new developments in the literature of optimization may thrust the advances of machine learning. On the other hand, we also interpret that the key task of learning is not simply optimization, as sometimes misunderstood in the optimization literature. We introduce the key challenges of learning and the current status of efforts towards the challenges. Furthermore, learning versus optimization has also been examined from a unified perspective under the name of Bayesian Ying-Yang learning, with combinatorial optimization made more effectively in help of learning.

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


27 TRIPLES      23 PREDICATES      27 URIs      15 LITERALS

Subject Predicate Object
1 articles:ecb72c2eb151baa4d331533713d25650 sg:abstract Both optimization and learning play important roles in a system for intelligent tasks. On one hand, we introduce three types of optimization tasks studied in the machine learning literature, corresponding to the three levels of inverse problems in an intelligent system. Also, we discuss three major roles of convexity in machine learning, either directly towards a convex programming or approximately transferring a difficult problem into a tractable one in help of local convexity and convex duality. No doubly, a good optimization algorithm takes an essential role in a learning process and new developments in the literature of optimization may thrust the advances of machine learning. On the other hand, we also interpret that the key task of learning is not simply optimization, as sometimes misunderstood in the optimization literature. We introduce the key challenges of learning and the current status of efforts towards the challenges. Furthermore, learning versus optimization has also been examined from a unified perspective under the name of Bayesian Ying-Yang learning, with combinatorial optimization made more effectively in help of learning.
2 sg:ddsIdJournalBrand iaor
3 sg:doi 10.1057/iaor.2010.4865
4 sg:doiLink http://dx.doi.org/10.1057/iaor.2010.4865
5 sg:hasArticleType article-types:research
6 sg:hasFieldOfResearchCode anzsrc-for:01
7 anzsrc-for:0103
8 anzsrc-for:08
9 anzsrc-for:0801
10 sg:hasJournal journals:1587f0c23f6d790a0b249e0af78a213d
11 journals:d654b82ffa89697399434ee935ac5bbb
12 sg:hasJournalBrand journal-brands:11eaa1206191d0347361452c8e00709c
13 sg:issnElectronic 1476-9352
14 sg:issnPrint 0020-580X
15 sg:issue 6
16 sg:license http://scigraph.springernature.com/explorer/license/
17 sg:npgId iaor20104865
18 sg:pageEnd
19 sg:pageStart
20 sg:publicationDate 2010-07-16
21 sg:publicationYear 2010
22 sg:publicationYearMonth 2010-07
23 sg:scigraphId ecb72c2eb151baa4d331533713d25650
24 sg:title Machine learning problems from optimization perspective
25 sg:volume 61
26 rdf:type sg:Article
27 rdfs:label Article: Machine learning problems from optimization perspective
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/articles/ecb72c2eb151baa4d331533713d25650'

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

curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/articles/ecb72c2eb151baa4d331533713d25650'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/articles/ecb72c2eb151baa4d331533713d25650'

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

curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/articles/ecb72c2eb151baa4d331533713d25650'






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


...