Bias and Variance Multi-objective Optimization for Support Vector Machines Model Selection View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2013

AUTHORS

Alejandro Rosales-Pérez , Hugo Jair Escalante , Jesus A. Gonzalez , Carlos A. Reyes-Garcia , Carlos A. Coello Coello

ABSTRACT

In this paper, we describe a novel model selection approach for a SVM. Each model can be composed by a feature selection method and a pre-processing method besides the classifier. Our approach is based on a multi-objective evolutionary algorithm and on the bias-variance definition. This strategy allows us to explore the hyperparameters space and to select the solutions with the best bias-variance trade-off. The proposed method is evaluated using a number of benchmark data sets for classification tasks. Experimental results show that it is possible to obtain models with an acceptable generalization performance using the proposed approach. More... »

PAGES

108-116

References to SciGraph publications

  • 2001-03. Soft Margins for AdaBoost in MACHINE LEARNING
  • 2000. A Fast Elitist Non-dominated Sorting Genetic Algorithm for Multi-objective Optimization: NSGA-II in PARALLEL PROBLEM SOLVING FROM NATURE PPSN VI
  • 2006. Multi-Objective Optimization of Support Vector Machines in MULTI-OBJECTIVE MACHINE LEARNING
  • 1997-03. On Bias, Variance, 0/1—Loss, and the Curse-of-Dimensionality in DATA MINING AND KNOWLEDGE DISCOVERY
  • 2000-08. MultiBoosting: A Technique for Combining Boosting and Wagging in MACHINE LEARNING
  • Book

    TITLE

    Pattern Recognition and Image Analysis

    ISBN

    978-3-642-38627-5
    978-3-642-38628-2

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-642-38628-2_12

    DOI

    http://dx.doi.org/10.1007/978-3-642-38628-2_12

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1026314231


    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": "National Institute of Astrophysics, Optics and Electronics", 
              "id": "https://www.grid.ac/institutes/grid.450293.9", 
              "name": [
                "Computer Science Department, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Tonantzintla, Puebla, Mexico"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Rosales-P\u00e9rez", 
            "givenName": "Alejandro", 
            "id": "sg:person.014420072025.69", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014420072025.69"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "National Institute of Astrophysics, Optics and Electronics", 
              "id": "https://www.grid.ac/institutes/grid.450293.9", 
              "name": [
                "Computer Science Department, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Tonantzintla, Puebla, Mexico"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Escalante", 
            "givenName": "Hugo Jair", 
            "id": "sg:person.01022621347.99", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01022621347.99"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "National Institute of Astrophysics, Optics and Electronics", 
              "id": "https://www.grid.ac/institutes/grid.450293.9", 
              "name": [
                "Computer Science Department, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Tonantzintla, Puebla, Mexico"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Gonzalez", 
            "givenName": "Jesus A.", 
            "id": "sg:person.010173104643.19", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010173104643.19"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "National Institute of Astrophysics, Optics and Electronics", 
              "id": "https://www.grid.ac/institutes/grid.450293.9", 
              "name": [
                "Computer Science Department, Instituto Nacional de Astrof\u00edsica, \u00d3ptica y Electr\u00f3nica (INAOE), Tonantzintla, Puebla, Mexico"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Reyes-Garcia", 
            "givenName": "Carlos A.", 
            "id": "sg:person.011206777361.46", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011206777361.46"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Instituto Polit\u00e9cnico Nacional", 
              "id": "https://www.grid.ac/institutes/grid.418275.d", 
              "name": [
                "Computer Science Department, CINVESTAV-IPN, Mexico City, Mexico"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Coello", 
            "givenName": "Carlos A. Coello", 
            "id": "sg:person.012160505340.13", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012160505340.13"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1023/a:1007618119488", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1003090683", 
              "https://doi.org/10.1023/a:1007618119488"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/b978-1-55860-377-6.50046-3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009692954"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1009778005914", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014832254", 
              "https://doi.org/10.1023/a:1009778005914"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45356-3_83", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019904657", 
              "https://doi.org/10.1007/3-540-45356-3_83"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45356-3_83", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019904657", 
              "https://doi.org/10.1007/3-540-45356-3_83"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.eswa.2010.11.066", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027480554"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-33019-4_9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1027603058", 
              "https://doi.org/10.1007/3-540-33019-4_9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.patcog.2009.07.006", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1029124909"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1007659514849", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1038080945", 
              "https://doi.org/10.1023/a:1007659514849"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/j.asoc.2009.11.003", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1042905923"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icnc.2010.5583912", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1093314647"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/icdar.2007.4378745", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1094132364"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2013", 
        "datePublishedReg": "2013-01-01", 
        "description": "In this paper, we describe a novel model selection approach for a SVM. Each model can be composed by a feature selection method and a pre-processing method besides the classifier. Our approach is based on a multi-objective evolutionary algorithm and on the bias-variance definition. This strategy allows us to explore the hyperparameters space and to select the solutions with the best bias-variance trade-off. The proposed method is evaluated using a number of benchmark data sets for classification tasks. Experimental results show that it is possible to obtain models with an acceptable generalization performance using the proposed approach.", 
        "editor": [
          {
            "familyName": "Sanches", 
            "givenName": "Jo\u00e3o M.", 
            "type": "Person"
          }, 
          {
            "familyName": "Mic\u00f3", 
            "givenName": "Luisa", 
            "type": "Person"
          }, 
          {
            "familyName": "Cardoso", 
            "givenName": "Jaime S.", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-642-38628-2_12", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": false, 
        "isPartOf": {
          "isbn": [
            "978-3-642-38627-5", 
            "978-3-642-38628-2"
          ], 
          "name": "Pattern Recognition and Image Analysis", 
          "type": "Book"
        }, 
        "name": "Bias and Variance Multi-objective Optimization for Support Vector Machines Model Selection", 
        "pagination": "108-116", 
        "productId": [
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-642-38628-2_12"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "7d5bd62593108f43ba9753ba17e8a9274f95a8bd3119461ff2ecb22521218a95"
            ]
          }, 
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1026314231"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-642-38628-2_12", 
          "https://app.dimensions.ai/details/publication/pub.1026314231"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-15T10:34", 
        "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/v90/0000000001_0000000264/records_8659_00000259.jsonl", 
        "type": "Chapter", 
        "url": "http://link.springer.com/10.1007/978-3-642-38628-2_12"
      }
    ]
     

    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.10.1007/978-3-642-38628-2_12'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-38628-2_12'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-38628-2_12'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-38628-2_12'


     

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

    144 TRIPLES      23 PREDICATES      38 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-642-38628-2_12 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N71780a86222b47bea616bcb37089ad2f
    4 schema:citation sg:pub.10.1007/3-540-33019-4_9
    5 sg:pub.10.1007/3-540-45356-3_83
    6 sg:pub.10.1023/a:1007618119488
    7 sg:pub.10.1023/a:1007659514849
    8 sg:pub.10.1023/a:1009778005914
    9 https://doi.org/10.1016/b978-1-55860-377-6.50046-3
    10 https://doi.org/10.1016/j.asoc.2009.11.003
    11 https://doi.org/10.1016/j.eswa.2010.11.066
    12 https://doi.org/10.1016/j.patcog.2009.07.006
    13 https://doi.org/10.1109/icdar.2007.4378745
    14 https://doi.org/10.1109/icnc.2010.5583912
    15 schema:datePublished 2013
    16 schema:datePublishedReg 2013-01-01
    17 schema:description In this paper, we describe a novel model selection approach for a SVM. Each model can be composed by a feature selection method and a pre-processing method besides the classifier. Our approach is based on a multi-objective evolutionary algorithm and on the bias-variance definition. This strategy allows us to explore the hyperparameters space and to select the solutions with the best bias-variance trade-off. The proposed method is evaluated using a number of benchmark data sets for classification tasks. Experimental results show that it is possible to obtain models with an acceptable generalization performance using the proposed approach.
    18 schema:editor N79f3164ce2d04c40986b14444fde14bc
    19 schema:genre chapter
    20 schema:inLanguage en
    21 schema:isAccessibleForFree false
    22 schema:isPartOf Nb322891f21804085ae81be42dca411d1
    23 schema:name Bias and Variance Multi-objective Optimization for Support Vector Machines Model Selection
    24 schema:pagination 108-116
    25 schema:productId N3626525fb63b4aaab593777e409b1dc6
    26 Ned1bf3a893024822b1b9f061fae1a779
    27 Nfcac1c9cdbaf49049b4585b8b20018b9
    28 schema:publisher Nefdcb098c885497db9bf45019545f976
    29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1026314231
    30 https://doi.org/10.1007/978-3-642-38628-2_12
    31 schema:sdDatePublished 2019-04-15T10:34
    32 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    33 schema:sdPublisher N877d7e0e347d488285f52de1a7ba3d86
    34 schema:url http://link.springer.com/10.1007/978-3-642-38628-2_12
    35 sgo:license sg:explorer/license/
    36 sgo:sdDataset chapters
    37 rdf:type schema:Chapter
    38 N00b9a9b36f9a493b80cab8d3aeb8f696 rdf:first sg:person.01022621347.99
    39 rdf:rest Nd873b9b3321340ad978bc8ff587a1773
    40 N026efeb39f234ef78ca2bfb74099dfaf rdf:first sg:person.012160505340.13
    41 rdf:rest rdf:nil
    42 N2b4de9a5557a48cc84417391f68a0bcb rdf:first N603172725a7f45a18bafe8d9dd1937fc
    43 rdf:rest Nf6489af67552467fbd4bc23da66b2d06
    44 N3626525fb63b4aaab593777e409b1dc6 schema:name readcube_id
    45 schema:value 7d5bd62593108f43ba9753ba17e8a9274f95a8bd3119461ff2ecb22521218a95
    46 rdf:type schema:PropertyValue
    47 N4c6741ad0b854a3685fddb1ecffbd53c rdf:first sg:person.011206777361.46
    48 rdf:rest N026efeb39f234ef78ca2bfb74099dfaf
    49 N603172725a7f45a18bafe8d9dd1937fc schema:familyName Micó
    50 schema:givenName Luisa
    51 rdf:type schema:Person
    52 N71780a86222b47bea616bcb37089ad2f rdf:first sg:person.014420072025.69
    53 rdf:rest N00b9a9b36f9a493b80cab8d3aeb8f696
    54 N79f3164ce2d04c40986b14444fde14bc rdf:first Ncaadf1b6e0044cd0a2f25eb0694b86ba
    55 rdf:rest N2b4de9a5557a48cc84417391f68a0bcb
    56 N877d7e0e347d488285f52de1a7ba3d86 schema:name Springer Nature - SN SciGraph project
    57 rdf:type schema:Organization
    58 N97e615527de34bffbe8084e6a2010164 schema:familyName Cardoso
    59 schema:givenName Jaime S.
    60 rdf:type schema:Person
    61 Nb322891f21804085ae81be42dca411d1 schema:isbn 978-3-642-38627-5
    62 978-3-642-38628-2
    63 schema:name Pattern Recognition and Image Analysis
    64 rdf:type schema:Book
    65 Ncaadf1b6e0044cd0a2f25eb0694b86ba schema:familyName Sanches
    66 schema:givenName João M.
    67 rdf:type schema:Person
    68 Nd873b9b3321340ad978bc8ff587a1773 rdf:first sg:person.010173104643.19
    69 rdf:rest N4c6741ad0b854a3685fddb1ecffbd53c
    70 Ned1bf3a893024822b1b9f061fae1a779 schema:name dimensions_id
    71 schema:value pub.1026314231
    72 rdf:type schema:PropertyValue
    73 Nefdcb098c885497db9bf45019545f976 schema:location Berlin, Heidelberg
    74 schema:name Springer Berlin Heidelberg
    75 rdf:type schema:Organisation
    76 Nf6489af67552467fbd4bc23da66b2d06 rdf:first N97e615527de34bffbe8084e6a2010164
    77 rdf:rest rdf:nil
    78 Nfcac1c9cdbaf49049b4585b8b20018b9 schema:name doi
    79 schema:value 10.1007/978-3-642-38628-2_12
    80 rdf:type schema:PropertyValue
    81 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    82 schema:name Information and Computing Sciences
    83 rdf:type schema:DefinedTerm
    84 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    85 schema:name Artificial Intelligence and Image Processing
    86 rdf:type schema:DefinedTerm
    87 sg:person.010173104643.19 schema:affiliation https://www.grid.ac/institutes/grid.450293.9
    88 schema:familyName Gonzalez
    89 schema:givenName Jesus A.
    90 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010173104643.19
    91 rdf:type schema:Person
    92 sg:person.01022621347.99 schema:affiliation https://www.grid.ac/institutes/grid.450293.9
    93 schema:familyName Escalante
    94 schema:givenName Hugo Jair
    95 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01022621347.99
    96 rdf:type schema:Person
    97 sg:person.011206777361.46 schema:affiliation https://www.grid.ac/institutes/grid.450293.9
    98 schema:familyName Reyes-Garcia
    99 schema:givenName Carlos A.
    100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011206777361.46
    101 rdf:type schema:Person
    102 sg:person.012160505340.13 schema:affiliation https://www.grid.ac/institutes/grid.418275.d
    103 schema:familyName Coello
    104 schema:givenName Carlos A. Coello
    105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012160505340.13
    106 rdf:type schema:Person
    107 sg:person.014420072025.69 schema:affiliation https://www.grid.ac/institutes/grid.450293.9
    108 schema:familyName Rosales-Pérez
    109 schema:givenName Alejandro
    110 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014420072025.69
    111 rdf:type schema:Person
    112 sg:pub.10.1007/3-540-33019-4_9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027603058
    113 https://doi.org/10.1007/3-540-33019-4_9
    114 rdf:type schema:CreativeWork
    115 sg:pub.10.1007/3-540-45356-3_83 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019904657
    116 https://doi.org/10.1007/3-540-45356-3_83
    117 rdf:type schema:CreativeWork
    118 sg:pub.10.1023/a:1007618119488 schema:sameAs https://app.dimensions.ai/details/publication/pub.1003090683
    119 https://doi.org/10.1023/a:1007618119488
    120 rdf:type schema:CreativeWork
    121 sg:pub.10.1023/a:1007659514849 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038080945
    122 https://doi.org/10.1023/a:1007659514849
    123 rdf:type schema:CreativeWork
    124 sg:pub.10.1023/a:1009778005914 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014832254
    125 https://doi.org/10.1023/a:1009778005914
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1016/b978-1-55860-377-6.50046-3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009692954
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1016/j.asoc.2009.11.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042905923
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1016/j.eswa.2010.11.066 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027480554
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1016/j.patcog.2009.07.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1029124909
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1109/icdar.2007.4378745 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094132364
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1109/icnc.2010.5583912 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093314647
    138 rdf:type schema:CreativeWork
    139 https://www.grid.ac/institutes/grid.418275.d schema:alternateName Instituto Politécnico Nacional
    140 schema:name Computer Science Department, CINVESTAV-IPN, Mexico City, Mexico
    141 rdf:type schema:Organization
    142 https://www.grid.ac/institutes/grid.450293.9 schema:alternateName National Institute of Astrophysics, Optics and Electronics
    143 schema:name Computer Science Department, Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE), Tonantzintla, Puebla, Mexico
    144 rdf:type schema:Organization
     




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


    ...