Hartigan’s Method for $$k$$ k -MLE: Mixture Modeling with Wishart Distributions and Its Application to Motion Retrieval View Full Text


Ontology type: schema:Chapter     


Chapter Info

DATE

2014

AUTHORS

Christophe Saint-Jean , Frank Nielsen

ABSTRACT

We describe a novel algorithm called \(k\)-Maximum Likelihood Estimator (\(k\)-MLE) for learning finite statistical mixtures of exponential families relying on Hartigan’s \(k\)-means swap clustering method. To illustrate this versatile Hartigan \(k\)-MLE technique, we consider the exponential family of Wishart distributions and show how to learn their mixtures. First, given a set of symmetric positive definite observation matrices, we provide an iterative algorithm to estimate the parameters of the underlying Wishart distribution which is guaranteed to converge to the MLE. Second, two initialization methods for \(k\)-MLE are proposed and compared. Finally, we propose to use the Cauchy-Schwartz statistical divergence as a dissimilarity measure between two Wishart mixture models and sketch a general methodology for building a motion retrieval system. More... »

PAGES

301-330

References to SciGraph publications

Book

TITLE

Geometric Theory of Information

ISBN

978-3-319-05316-5
978-3-319-05317-2

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-05317-2_11

DOI

http://dx.doi.org/10.1007/978-3-319-05317-2_11

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1043156069


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/2008/0104", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Statistics", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of La Rochelle", 
          "id": "https://www.grid.ac/institutes/grid.11698.37", 
          "name": [
            "Math\u00e9matiques, Image, Applications (MIA), Universit\u00e9 de La Rochelle, 17000\u00a0La\u00a0Rochelle, France"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Saint-Jean", 
        "givenName": "Christophe", 
        "id": "sg:person.016700276413.20", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016700276413.20"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Sony Computer Science Laboratories", 
          "id": "https://www.grid.ac/institutes/grid.452725.3", 
          "name": [
            "Sony Computer Science Laboratories, Inc., 3-14-13 Higashi Gotanda, 141-0022\u00a0\u00a0Shinagawa-Ku, Tokyo, Japan"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Nielsen", 
        "givenName": "Frank", 
        "id": "sg:person.012062051333.43", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012062051333.43"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1109/tnn.2005.845141", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002360675"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tnn.2005.845141", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002360675"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/0167-9473(92)90042-e", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1009547665"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/978-3-540-73273-0_32", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1015785433", 
          "https://doi.org/10.1007/978-3-540-73273-0_32"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/bf00940196", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1018676235", 
          "https://doi.org/10.1007/bf00940196"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2009.09.011", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1019119600"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1214/11-aos951", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1021386685"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1080/02331880008802323", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1028589697"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.patrec.2010.07.002", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1037067104"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1111/1467-9469.00317", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1045828951"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.jmva.2006.09.008", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053164331"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1093/biomet/20a.1-2.32", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1059415568"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/jstsp.2010.2101579", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061338049"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tpami.2006.85", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061743127"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/icassp.2012.6288022", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094698632"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cvpr.2011.5995723", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095621780"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2014", 
    "datePublishedReg": "2014-01-01", 
    "description": "We describe a novel algorithm called \\(k\\)-Maximum Likelihood Estimator (\\(k\\)-MLE) for learning finite statistical mixtures of exponential families relying on Hartigan\u2019s \\(k\\)-means swap clustering method. To illustrate this versatile Hartigan \\(k\\)-MLE technique, we consider the exponential family of Wishart distributions and show how to learn their mixtures. First, given a set of symmetric positive definite observation matrices, we provide an iterative algorithm to estimate the parameters of the underlying Wishart distribution which is guaranteed to converge to the MLE. Second, two initialization methods for \\(k\\)-MLE are proposed and compared. Finally, we propose to use the Cauchy-Schwartz statistical divergence as a dissimilarity measure between two Wishart mixture models and sketch a general methodology for building a motion retrieval system.", 
    "editor": [
      {
        "familyName": "Nielsen", 
        "givenName": "Frank", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-05317-2_11", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": false, 
    "isPartOf": {
      "isbn": [
        "978-3-319-05316-5", 
        "978-3-319-05317-2"
      ], 
      "name": "Geometric Theory of Information", 
      "type": "Book"
    }, 
    "name": "Hartigan\u2019s Method for $$k$$ k -MLE: Mixture Modeling with Wishart Distributions and Its Application to Motion Retrieval", 
    "pagination": "301-330", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-05317-2_11"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "cd9108038e2ea7ca8191bdad5787b72180ec965b02f091501f1410adb0215bde"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1043156069"
        ]
      }
    ], 
    "publisher": {
      "location": "Cham", 
      "name": "Springer International Publishing", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-05317-2_11", 
      "https://app.dimensions.ai/details/publication/pub.1043156069"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T14:27", 
    "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_8669_00000270.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-319-05317-2_11"
  }
]
 

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.10.1007/978-3-319-05317-2_11'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-05317-2_11'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-05317-2_11'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-05317-2_11'


 

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

122 TRIPLES      23 PREDICATES      42 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-05317-2_11 schema:about anzsrc-for:01
2 anzsrc-for:0104
3 schema:author N02e18b16893d456287ea063a1d85763b
4 schema:citation sg:pub.10.1007/978-3-540-73273-0_32
5 sg:pub.10.1007/bf00940196
6 https://doi.org/10.1016/0167-9473(92)90042-e
7 https://doi.org/10.1016/j.jmva.2006.09.008
8 https://doi.org/10.1016/j.patrec.2009.09.011
9 https://doi.org/10.1016/j.patrec.2010.07.002
10 https://doi.org/10.1080/02331880008802323
11 https://doi.org/10.1093/biomet/20a.1-2.32
12 https://doi.org/10.1109/cvpr.2011.5995723
13 https://doi.org/10.1109/icassp.2012.6288022
14 https://doi.org/10.1109/jstsp.2010.2101579
15 https://doi.org/10.1109/tnn.2005.845141
16 https://doi.org/10.1109/tpami.2006.85
17 https://doi.org/10.1111/1467-9469.00317
18 https://doi.org/10.1214/11-aos951
19 schema:datePublished 2014
20 schema:datePublishedReg 2014-01-01
21 schema:description We describe a novel algorithm called \(k\)-Maximum Likelihood Estimator (\(k\)-MLE) for learning finite statistical mixtures of exponential families relying on Hartigan’s \(k\)-means swap clustering method. To illustrate this versatile Hartigan \(k\)-MLE technique, we consider the exponential family of Wishart distributions and show how to learn their mixtures. First, given a set of symmetric positive definite observation matrices, we provide an iterative algorithm to estimate the parameters of the underlying Wishart distribution which is guaranteed to converge to the MLE. Second, two initialization methods for \(k\)-MLE are proposed and compared. Finally, we propose to use the Cauchy-Schwartz statistical divergence as a dissimilarity measure between two Wishart mixture models and sketch a general methodology for building a motion retrieval system.
22 schema:editor Nb8b03c6b57f64a77809ede970a097f1f
23 schema:genre chapter
24 schema:inLanguage en
25 schema:isAccessibleForFree false
26 schema:isPartOf N326022b7ba4a4882a5fc02716ebf443c
27 schema:name Hartigan’s Method for $$k$$ k -MLE: Mixture Modeling with Wishart Distributions and Its Application to Motion Retrieval
28 schema:pagination 301-330
29 schema:productId N2d58196d9d2c4479b9b4339a5bed7322
30 N7b06da7b84e44cf0a24a1e64e3936f41
31 Nf26df60075ac46b5b9b30edba42cce5c
32 schema:publisher N25a1838740ae4ee1bd7b94105eb8328a
33 schema:sameAs https://app.dimensions.ai/details/publication/pub.1043156069
34 https://doi.org/10.1007/978-3-319-05317-2_11
35 schema:sdDatePublished 2019-04-15T14:27
36 schema:sdLicense https://scigraph.springernature.com/explorer/license/
37 schema:sdPublisher N398e03534869476fbe0ed2ed18944004
38 schema:url http://link.springer.com/10.1007/978-3-319-05317-2_11
39 sgo:license sg:explorer/license/
40 sgo:sdDataset chapters
41 rdf:type schema:Chapter
42 N011b396e87254e9eb8b5d9f0c2fb3658 rdf:first sg:person.012062051333.43
43 rdf:rest rdf:nil
44 N02e18b16893d456287ea063a1d85763b rdf:first sg:person.016700276413.20
45 rdf:rest N011b396e87254e9eb8b5d9f0c2fb3658
46 N25a1838740ae4ee1bd7b94105eb8328a schema:location Cham
47 schema:name Springer International Publishing
48 rdf:type schema:Organisation
49 N2d58196d9d2c4479b9b4339a5bed7322 schema:name doi
50 schema:value 10.1007/978-3-319-05317-2_11
51 rdf:type schema:PropertyValue
52 N326022b7ba4a4882a5fc02716ebf443c schema:isbn 978-3-319-05316-5
53 978-3-319-05317-2
54 schema:name Geometric Theory of Information
55 rdf:type schema:Book
56 N398e03534869476fbe0ed2ed18944004 schema:name Springer Nature - SN SciGraph project
57 rdf:type schema:Organization
58 N7b06da7b84e44cf0a24a1e64e3936f41 schema:name readcube_id
59 schema:value cd9108038e2ea7ca8191bdad5787b72180ec965b02f091501f1410adb0215bde
60 rdf:type schema:PropertyValue
61 N84e538b057814ad1813e2840afab1f81 schema:familyName Nielsen
62 schema:givenName Frank
63 rdf:type schema:Person
64 Nb8b03c6b57f64a77809ede970a097f1f rdf:first N84e538b057814ad1813e2840afab1f81
65 rdf:rest rdf:nil
66 Nf26df60075ac46b5b9b30edba42cce5c schema:name dimensions_id
67 schema:value pub.1043156069
68 rdf:type schema:PropertyValue
69 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
70 schema:name Mathematical Sciences
71 rdf:type schema:DefinedTerm
72 anzsrc-for:0104 schema:inDefinedTermSet anzsrc-for:
73 schema:name Statistics
74 rdf:type schema:DefinedTerm
75 sg:person.012062051333.43 schema:affiliation https://www.grid.ac/institutes/grid.452725.3
76 schema:familyName Nielsen
77 schema:givenName Frank
78 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012062051333.43
79 rdf:type schema:Person
80 sg:person.016700276413.20 schema:affiliation https://www.grid.ac/institutes/grid.11698.37
81 schema:familyName Saint-Jean
82 schema:givenName Christophe
83 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016700276413.20
84 rdf:type schema:Person
85 sg:pub.10.1007/978-3-540-73273-0_32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1015785433
86 https://doi.org/10.1007/978-3-540-73273-0_32
87 rdf:type schema:CreativeWork
88 sg:pub.10.1007/bf00940196 schema:sameAs https://app.dimensions.ai/details/publication/pub.1018676235
89 https://doi.org/10.1007/bf00940196
90 rdf:type schema:CreativeWork
91 https://doi.org/10.1016/0167-9473(92)90042-e schema:sameAs https://app.dimensions.ai/details/publication/pub.1009547665
92 rdf:type schema:CreativeWork
93 https://doi.org/10.1016/j.jmva.2006.09.008 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053164331
94 rdf:type schema:CreativeWork
95 https://doi.org/10.1016/j.patrec.2009.09.011 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019119600
96 rdf:type schema:CreativeWork
97 https://doi.org/10.1016/j.patrec.2010.07.002 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037067104
98 rdf:type schema:CreativeWork
99 https://doi.org/10.1080/02331880008802323 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028589697
100 rdf:type schema:CreativeWork
101 https://doi.org/10.1093/biomet/20a.1-2.32 schema:sameAs https://app.dimensions.ai/details/publication/pub.1059415568
102 rdf:type schema:CreativeWork
103 https://doi.org/10.1109/cvpr.2011.5995723 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095621780
104 rdf:type schema:CreativeWork
105 https://doi.org/10.1109/icassp.2012.6288022 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094698632
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1109/jstsp.2010.2101579 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061338049
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1109/tnn.2005.845141 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002360675
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1109/tpami.2006.85 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061743127
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1111/1467-9469.00317 schema:sameAs https://app.dimensions.ai/details/publication/pub.1045828951
114 rdf:type schema:CreativeWork
115 https://doi.org/10.1214/11-aos951 schema:sameAs https://app.dimensions.ai/details/publication/pub.1021386685
116 rdf:type schema:CreativeWork
117 https://www.grid.ac/institutes/grid.11698.37 schema:alternateName University of La Rochelle
118 schema:name Mathématiques, Image, Applications (MIA), Université de La Rochelle, 17000 La Rochelle, France
119 rdf:type schema:Organization
120 https://www.grid.ac/institutes/grid.452725.3 schema:alternateName Sony Computer Science Laboratories
121 schema:name Sony Computer Science Laboratories, Inc., 3-14-13 Higashi Gotanda, 141-0022  Shinagawa-Ku, Tokyo, Japan
122 rdf:type schema:Organization
 




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


...