Support vector machine classification with indefinite kernels View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2009-10

AUTHORS

Ronny Luss, Alexandre d’Aspremont

ABSTRACT

We propose a method for support vector machine classification using indefinite kernels. Instead of directly minimizing or stabilizing a nonconvex loss function, our algorithm simultaneously computes support vectors and a proxy kernel matrix used in forming the loss. This can be interpreted as a penalized kernel learning problem where indefinite kernel matrices are treated as noisy observations of a true Mercer kernel. Our formulation keeps the problem convex and relatively large problems can be solved efficiently using the projected gradient or analytic center cutting plane methods. We compare the performance of our technique with other methods on several standard data sets. More... »

PAGES

97-118

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/s12532-009-0005-5

DOI

http://dx.doi.org/10.1007/s12532-009-0005-5

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1022274372


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Princeton University", 
          "id": "https://www.grid.ac/institutes/grid.16750.35", 
          "name": [
            "ORFE Department, Princeton University, 08544, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Luss", 
        "givenName": "Ronny", 
        "id": "sg:person.016456423716.19", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016456423716.19"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Princeton University", 
          "id": "https://www.grid.ac/institutes/grid.16750.35", 
          "name": [
            "ORFE Department, Princeton University, 08544, Princeton, NJ, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "d\u2019Aspremont", 
        "givenName": "Alexandre", 
        "id": "sg:person.012750457111.14", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012750457111.14"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1145/1015330.1015424", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1005040776"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1143844.1143908", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1013799066"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1390156.1390174", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015250931"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/1055678021000060829a", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017066776"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1553374.1553393", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1024910505"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-49430-8_13", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026545665", 
          "https://doi.org/10.1007/3-540-49430-8_13"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/3-540-49430-8_13", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026545665", 
          "https://doi.org/10.1007/3-540-49430-8_13"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://app.dimensions.ai/details/publication/pub.1026756433", 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-662-02796-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026756433", 
          "https://doi.org/10.1007/978-3-662-02796-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-662-02796-7", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1026756433", 
          "https://doi.org/10.1007/978-3-662-02796-7"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/bioinformatics/bth141", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1035544988"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1057/palgrave.jors.2600425", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1039205956", 
          "https://doi.org/10.1057/palgrave.jors.2600425"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/imanum/22.3.329", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1059688980"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/34.291440", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061155985"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2005.78", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061742933"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/0802007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062854158"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/1035089", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062863545"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10107980004a", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083414997", 
          "https://doi.org/10.1007/s10107980004a"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icdm.2006.60", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093185890"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icdm.2006.60", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093185890"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icpr.2002.1048439", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093203821"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cbmi.2007.385386", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094821975"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/1.9781611971446", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098555836"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1017/cbo9780511804441", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1098700691"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2009-10", 
    "datePublishedReg": "2009-10-01", 
    "description": "We propose a method for support vector machine classification using indefinite kernels. Instead of directly minimizing or stabilizing a nonconvex loss function, our algorithm simultaneously computes support vectors and a proxy kernel matrix used in forming the loss. This can be interpreted as a penalized kernel learning problem where indefinite kernel matrices are treated as noisy observations of a true Mercer kernel. Our formulation keeps the problem convex and relatively large problems can be solved efficiently using the projected gradient or analytic center cutting plane methods. We compare the performance of our technique with other methods on several standard data sets.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1007/s12532-009-0005-5", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": [
      {
        "id": "sg:journal.1053027", 
        "issn": [
          "1867-2949", 
          "1867-2957"
        ], 
        "name": "Mathematical Programming Computation", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "2-3", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "1"
      }
    ], 
    "name": "Support vector machine classification with indefinite kernels", 
    "pagination": "97-118", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "6a1ead6580b03edf8338760b918563e8217236634e8a3cd7b9c8907ad1301050"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/s12532-009-0005-5"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1022274372"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1007/s12532-009-0005-5", 
      "https://app.dimensions.ai/details/publication/pub.1022274372"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T09:24", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000345_0000000345/records_64094_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "http://link.springer.com/10.1007%2Fs12532-009-0005-5"
  }
]
 

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

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/s12532-009-0005-5'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/s12532-009-0005-5'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s12532-009-0005-5'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s12532-009-0005-5'


 

This table displays all metadata directly associated to this object as RDF triples.

134 TRIPLES      21 PREDICATES      48 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/s12532-009-0005-5 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nead365a11c8f408aa488787f2ddb370e
4 schema:citation sg:pub.10.1007/3-540-49430-8_13
5 sg:pub.10.1007/978-3-662-02796-7
6 sg:pub.10.1007/s10107980004a
7 sg:pub.10.1057/palgrave.jors.2600425
8 https://app.dimensions.ai/details/publication/pub.1026756433
9 https://doi.org/10.1017/cbo9780511804441
10 https://doi.org/10.1080/1055678021000060829a
11 https://doi.org/10.1093/bioinformatics/bth141
12 https://doi.org/10.1093/imanum/22.3.329
13 https://doi.org/10.1109/34.291440
14 https://doi.org/10.1109/cbmi.2007.385386
15 https://doi.org/10.1109/icdm.2006.60
16 https://doi.org/10.1109/icpr.2002.1048439
17 https://doi.org/10.1109/tpami.2005.78
18 https://doi.org/10.1137/0802007
19 https://doi.org/10.1137/1.9781611971446
20 https://doi.org/10.1137/1035089
21 https://doi.org/10.1145/1015330.1015424
22 https://doi.org/10.1145/1143844.1143908
23 https://doi.org/10.1145/1390156.1390174
24 https://doi.org/10.1145/1553374.1553393
25 schema:datePublished 2009-10
26 schema:datePublishedReg 2009-10-01
27 schema:description We propose a method for support vector machine classification using indefinite kernels. Instead of directly minimizing or stabilizing a nonconvex loss function, our algorithm simultaneously computes support vectors and a proxy kernel matrix used in forming the loss. This can be interpreted as a penalized kernel learning problem where indefinite kernel matrices are treated as noisy observations of a true Mercer kernel. Our formulation keeps the problem convex and relatively large problems can be solved efficiently using the projected gradient or analytic center cutting plane methods. We compare the performance of our technique with other methods on several standard data sets.
28 schema:genre research_article
29 schema:inLanguage en
30 schema:isAccessibleForFree true
31 schema:isPartOf N1579f175876242438e00b8ff171b82e4
32 Nc5f2a0aa7cbf4f8e9a3cbfc53cfa32ad
33 sg:journal.1053027
34 schema:name Support vector machine classification with indefinite kernels
35 schema:pagination 97-118
36 schema:productId N3253d727e765421e8032c89f5fff0dc8
37 N408ad781fd524dfba5eac0957bcd92cb
38 N6dff40b5eaac4042b65be95378a81c47
39 schema:sameAs https://app.dimensions.ai/details/publication/pub.1022274372
40 https://doi.org/10.1007/s12532-009-0005-5
41 schema:sdDatePublished 2019-04-11T09:24
42 schema:sdLicense https://scigraph.springernature.com/explorer/license/
43 schema:sdPublisher Nc1c7e7809a754ee7b2c69e7d4317c5f0
44 schema:url http://link.springer.com/10.1007%2Fs12532-009-0005-5
45 sgo:license sg:explorer/license/
46 sgo:sdDataset articles
47 rdf:type schema:ScholarlyArticle
48 N1579f175876242438e00b8ff171b82e4 schema:volumeNumber 1
49 rdf:type schema:PublicationVolume
50 N3253d727e765421e8032c89f5fff0dc8 schema:name readcube_id
51 schema:value 6a1ead6580b03edf8338760b918563e8217236634e8a3cd7b9c8907ad1301050
52 rdf:type schema:PropertyValue
53 N408ad781fd524dfba5eac0957bcd92cb schema:name doi
54 schema:value 10.1007/s12532-009-0005-5
55 rdf:type schema:PropertyValue
56 N6dff40b5eaac4042b65be95378a81c47 schema:name dimensions_id
57 schema:value pub.1022274372
58 rdf:type schema:PropertyValue
59 N6f8444940586410b92d2002d34db9a17 rdf:first sg:person.012750457111.14
60 rdf:rest rdf:nil
61 Nc1c7e7809a754ee7b2c69e7d4317c5f0 schema:name Springer Nature - SN SciGraph project
62 rdf:type schema:Organization
63 Nc5f2a0aa7cbf4f8e9a3cbfc53cfa32ad schema:issueNumber 2-3
64 rdf:type schema:PublicationIssue
65 Nead365a11c8f408aa488787f2ddb370e rdf:first sg:person.016456423716.19
66 rdf:rest N6f8444940586410b92d2002d34db9a17
67 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
68 schema:name Information and Computing Sciences
69 rdf:type schema:DefinedTerm
70 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
71 schema:name Artificial Intelligence and Image Processing
72 rdf:type schema:DefinedTerm
73 sg:journal.1053027 schema:issn 1867-2949
74 1867-2957
75 schema:name Mathematical Programming Computation
76 rdf:type schema:Periodical
77 sg:person.012750457111.14 schema:affiliation https://www.grid.ac/institutes/grid.16750.35
78 schema:familyName d’Aspremont
79 schema:givenName Alexandre
80 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012750457111.14
81 rdf:type schema:Person
82 sg:person.016456423716.19 schema:affiliation https://www.grid.ac/institutes/grid.16750.35
83 schema:familyName Luss
84 schema:givenName Ronny
85 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016456423716.19
86 rdf:type schema:Person
87 sg:pub.10.1007/3-540-49430-8_13 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026545665
88 https://doi.org/10.1007/3-540-49430-8_13
89 rdf:type schema:CreativeWork
90 sg:pub.10.1007/978-3-662-02796-7 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026756433
91 https://doi.org/10.1007/978-3-662-02796-7
92 rdf:type schema:CreativeWork
93 sg:pub.10.1007/s10107980004a schema:sameAs https://app.dimensions.ai/details/publication/pub.1083414997
94 https://doi.org/10.1007/s10107980004a
95 rdf:type schema:CreativeWork
96 sg:pub.10.1057/palgrave.jors.2600425 schema:sameAs https://app.dimensions.ai/details/publication/pub.1039205956
97 https://doi.org/10.1057/palgrave.jors.2600425
98 rdf:type schema:CreativeWork
99 https://app.dimensions.ai/details/publication/pub.1026756433 schema:CreativeWork
100 https://doi.org/10.1017/cbo9780511804441 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098700691
101 rdf:type schema:CreativeWork
102 https://doi.org/10.1080/1055678021000060829a schema:sameAs https://app.dimensions.ai/details/publication/pub.1017066776
103 rdf:type schema:CreativeWork
104 https://doi.org/10.1093/bioinformatics/bth141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1035544988
105 rdf:type schema:CreativeWork
106 https://doi.org/10.1093/imanum/22.3.329 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059688980
107 rdf:type schema:CreativeWork
108 https://doi.org/10.1109/34.291440 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061155985
109 rdf:type schema:CreativeWork
110 https://doi.org/10.1109/cbmi.2007.385386 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094821975
111 rdf:type schema:CreativeWork
112 https://doi.org/10.1109/icdm.2006.60 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093185890
113 rdf:type schema:CreativeWork
114 https://doi.org/10.1109/icpr.2002.1048439 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093203821
115 rdf:type schema:CreativeWork
116 https://doi.org/10.1109/tpami.2005.78 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061742933
117 rdf:type schema:CreativeWork
118 https://doi.org/10.1137/0802007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062854158
119 rdf:type schema:CreativeWork
120 https://doi.org/10.1137/1.9781611971446 schema:sameAs https://app.dimensions.ai/details/publication/pub.1098555836
121 rdf:type schema:CreativeWork
122 https://doi.org/10.1137/1035089 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062863545
123 rdf:type schema:CreativeWork
124 https://doi.org/10.1145/1015330.1015424 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005040776
125 rdf:type schema:CreativeWork
126 https://doi.org/10.1145/1143844.1143908 schema:sameAs https://app.dimensions.ai/details/publication/pub.1013799066
127 rdf:type schema:CreativeWork
128 https://doi.org/10.1145/1390156.1390174 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015250931
129 rdf:type schema:CreativeWork
130 https://doi.org/10.1145/1553374.1553393 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024910505
131 rdf:type schema:CreativeWork
132 https://www.grid.ac/institutes/grid.16750.35 schema:alternateName Princeton University
133 schema:name ORFE Department, Princeton University, 08544, Princeton, NJ, USA
134 rdf:type schema:Organization
 




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


...