Bilevel Optimization with Nonsmooth Lower Level Problems View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2015-04-28

AUTHORS

Peter Ochs , René Ranftl , Thomas Brox , Thomas Pock

ABSTRACT

We consider a bilevel optimization approach for parameter learning in nonsmooth variational models. Existing approaches solve this problem by applying implicit differentiation to a sufficiently smooth approximation of the nondifferentiable lower level problem. We propose an alternative method based on differentiating the iterations of a nonlinear primal–dual algorithm. Our method computes exact (sub)gradients and can be applied also in the nonsmooth setting. We show preliminary results for the case of multi-label image segmentation. More... »

PAGES

654-665

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-319-18461-6_52

DOI

http://dx.doi.org/10.1007/978-3-319-18461-6_52

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1041058839


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/2008/01", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Mathematical Sciences", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0103", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Numerical and Computational Mathematics", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "Computer Vision Group, University of Freiburg, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Computer Vision Group, University of Freiburg, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ochs", 
        "givenName": "Peter", 
        "id": "sg:person.011151475055.48", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011151475055.48"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria", 
          "id": "http://www.grid.ac/institutes/grid.410413.3", 
          "name": [
            "Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ranftl", 
        "givenName": "Ren\u00e9", 
        "id": "sg:person.013557163412.33", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013557163412.33"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Computer Vision Group, University of Freiburg, Freiburg, Germany", 
          "id": "http://www.grid.ac/institutes/grid.5963.9", 
          "name": [
            "Computer Vision Group, University of Freiburg, Freiburg, Germany"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Brox", 
        "givenName": "Thomas", 
        "id": "sg:person.012443225372.65", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Digital Safety and Security Department, AIT Austrian Institute of Technology GmbH, 1220, Vienna, Austria", 
          "id": "http://www.grid.ac/institutes/grid.4332.6", 
          "name": [
            "Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria", 
            "Digital Safety and Security Department, AIT Austrian Institute of Technology GmbH, 1220, Vienna, Austria"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Pock", 
        "givenName": "Thomas", 
        "id": "sg:person.015744126036.09", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015744126036.09"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2015-04-28", 
    "datePublishedReg": "2015-04-28", 
    "description": "We consider a bilevel optimization approach for parameter learning in nonsmooth variational models. Existing approaches solve this problem by applying implicit differentiation to a sufficiently smooth approximation of the nondifferentiable lower level problem. We propose an alternative method based on differentiating the iterations of a nonlinear primal\u2013dual algorithm. Our method computes exact (sub)gradients and can be applied also in the nonsmooth setting. We show preliminary results for the case of multi-label image segmentation.", 
    "editor": [
      {
        "familyName": "Aujol", 
        "givenName": "Jean-Fran\u00e7ois", 
        "type": "Person"
      }, 
      {
        "familyName": "Nikolova", 
        "givenName": "Mila", 
        "type": "Person"
      }, 
      {
        "familyName": "Papadakis", 
        "givenName": "Nicolas", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-319-18461-6_52", 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-319-18460-9", 
        "978-3-319-18461-6"
      ], 
      "name": "Scale Space and Variational Methods in Computer Vision", 
      "type": "Book"
    }, 
    "keywords": [
      "level problem", 
      "bilevel optimization approach", 
      "lower level problem", 
      "primal-dual algorithm", 
      "multi-label image segmentation", 
      "smooth approximation", 
      "nonsmooth setting", 
      "bilevel optimization", 
      "implicit differentiation", 
      "optimization approach", 
      "variational model", 
      "problem", 
      "approximation", 
      "iteration", 
      "image segmentation", 
      "Existing approaches", 
      "optimization", 
      "alternative method", 
      "algorithm", 
      "approach", 
      "parameters", 
      "model", 
      "preliminary results", 
      "cases", 
      "segmentation", 
      "results", 
      "setting", 
      "differentiation", 
      "method"
    ], 
    "name": "Bilevel Optimization with Nonsmooth Lower Level Problems", 
    "pagination": "654-665", 
    "productId": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1041058839"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-319-18461-6_52"
        ]
      }
    ], 
    "publisher": {
      "name": "Springer Nature", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-319-18461-6_52", 
      "https://app.dimensions.ai/details/publication/pub.1041058839"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2022-10-01T06:52", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-springernature-scigraph/baseset/20221001/entities/gbq_results/chapter/chapter_110.jsonl", 
    "type": "Chapter", 
    "url": "https://doi.org/10.1007/978-3-319-18461-6_52"
  }
]
 

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.10.1007/978-3-319-18461-6_52'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-18461-6_52'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-18461-6_52'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-319-18461-6_52'


 

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

126 TRIPLES      22 PREDICATES      53 URIs      46 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-319-18461-6_52 schema:about anzsrc-for:01
2 anzsrc-for:0103
3 schema:author Na03794922994433295435112daa02538
4 schema:datePublished 2015-04-28
5 schema:datePublishedReg 2015-04-28
6 schema:description We consider a bilevel optimization approach for parameter learning in nonsmooth variational models. Existing approaches solve this problem by applying implicit differentiation to a sufficiently smooth approximation of the nondifferentiable lower level problem. We propose an alternative method based on differentiating the iterations of a nonlinear primal–dual algorithm. Our method computes exact (sub)gradients and can be applied also in the nonsmooth setting. We show preliminary results for the case of multi-label image segmentation.
7 schema:editor N2fcb194e300a4370a68d35d8d26654c4
8 schema:genre chapter
9 schema:isAccessibleForFree true
10 schema:isPartOf Nf0e46e9f73a74f069966955905aa90f1
11 schema:keywords Existing approaches
12 algorithm
13 alternative method
14 approach
15 approximation
16 bilevel optimization
17 bilevel optimization approach
18 cases
19 differentiation
20 image segmentation
21 implicit differentiation
22 iteration
23 level problem
24 lower level problem
25 method
26 model
27 multi-label image segmentation
28 nonsmooth setting
29 optimization
30 optimization approach
31 parameters
32 preliminary results
33 primal-dual algorithm
34 problem
35 results
36 segmentation
37 setting
38 smooth approximation
39 variational model
40 schema:name Bilevel Optimization with Nonsmooth Lower Level Problems
41 schema:pagination 654-665
42 schema:productId N14fdcb367d2d4e75807f2d0e88cb673f
43 Nd5d9f14ca9a54dde88af2ab91ad397e5
44 schema:publisher N8af68e1f4a4144b194ca2042f121812d
45 schema:sameAs https://app.dimensions.ai/details/publication/pub.1041058839
46 https://doi.org/10.1007/978-3-319-18461-6_52
47 schema:sdDatePublished 2022-10-01T06:52
48 schema:sdLicense https://scigraph.springernature.com/explorer/license/
49 schema:sdPublisher N3cf7bcb4184348b78e8da5e2e159d804
50 schema:url https://doi.org/10.1007/978-3-319-18461-6_52
51 sgo:license sg:explorer/license/
52 sgo:sdDataset chapters
53 rdf:type schema:Chapter
54 N0957449356ba4ab8be492a1ab7447755 rdf:first N9e1ff9e2337e477990fdf1202f636ba5
55 rdf:rest rdf:nil
56 N14fdcb367d2d4e75807f2d0e88cb673f schema:name dimensions_id
57 schema:value pub.1041058839
58 rdf:type schema:PropertyValue
59 N266b46489ecb4e388f9c91252f7e7307 rdf:first sg:person.012443225372.65
60 rdf:rest N326f27228a3e484eb68cb4ddd8ff36e4
61 N2fcb194e300a4370a68d35d8d26654c4 rdf:first Nf72d259e26f4419a8d34a84c1879a75f
62 rdf:rest Nd8610c52233344e48504238afca02d98
63 N326f27228a3e484eb68cb4ddd8ff36e4 rdf:first sg:person.015744126036.09
64 rdf:rest rdf:nil
65 N3cf7bcb4184348b78e8da5e2e159d804 schema:name Springer Nature - SN SciGraph project
66 rdf:type schema:Organization
67 N4ac045fe3b0147bc8bb58ce56c0fc3cd schema:familyName Nikolova
68 schema:givenName Mila
69 rdf:type schema:Person
70 N8af68e1f4a4144b194ca2042f121812d schema:name Springer Nature
71 rdf:type schema:Organisation
72 N9e1ff9e2337e477990fdf1202f636ba5 schema:familyName Papadakis
73 schema:givenName Nicolas
74 rdf:type schema:Person
75 Na03794922994433295435112daa02538 rdf:first sg:person.011151475055.48
76 rdf:rest Nc652ef44e7b44fcf8274f3b8cb0d8bd1
77 Nc652ef44e7b44fcf8274f3b8cb0d8bd1 rdf:first sg:person.013557163412.33
78 rdf:rest N266b46489ecb4e388f9c91252f7e7307
79 Nd5d9f14ca9a54dde88af2ab91ad397e5 schema:name doi
80 schema:value 10.1007/978-3-319-18461-6_52
81 rdf:type schema:PropertyValue
82 Nd8610c52233344e48504238afca02d98 rdf:first N4ac045fe3b0147bc8bb58ce56c0fc3cd
83 rdf:rest N0957449356ba4ab8be492a1ab7447755
84 Nf0e46e9f73a74f069966955905aa90f1 schema:isbn 978-3-319-18460-9
85 978-3-319-18461-6
86 schema:name Scale Space and Variational Methods in Computer Vision
87 rdf:type schema:Book
88 Nf72d259e26f4419a8d34a84c1879a75f schema:familyName Aujol
89 schema:givenName Jean-François
90 rdf:type schema:Person
91 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
92 schema:name Mathematical Sciences
93 rdf:type schema:DefinedTerm
94 anzsrc-for:0103 schema:inDefinedTermSet anzsrc-for:
95 schema:name Numerical and Computational Mathematics
96 rdf:type schema:DefinedTerm
97 sg:person.011151475055.48 schema:affiliation grid-institutes:grid.5963.9
98 schema:familyName Ochs
99 schema:givenName Peter
100 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.011151475055.48
101 rdf:type schema:Person
102 sg:person.012443225372.65 schema:affiliation grid-institutes:grid.5963.9
103 schema:familyName Brox
104 schema:givenName Thomas
105 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.012443225372.65
106 rdf:type schema:Person
107 sg:person.013557163412.33 schema:affiliation grid-institutes:grid.410413.3
108 schema:familyName Ranftl
109 schema:givenName René
110 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013557163412.33
111 rdf:type schema:Person
112 sg:person.015744126036.09 schema:affiliation grid-institutes:grid.4332.6
113 schema:familyName Pock
114 schema:givenName Thomas
115 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015744126036.09
116 rdf:type schema:Person
117 grid-institutes:grid.410413.3 schema:alternateName Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria
118 schema:name Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria
119 rdf:type schema:Organization
120 grid-institutes:grid.4332.6 schema:alternateName Digital Safety and Security Department, AIT Austrian Institute of Technology GmbH, 1220, Vienna, Austria
121 schema:name Digital Safety and Security Department, AIT Austrian Institute of Technology GmbH, 1220, Vienna, Austria
122 Institute for Computer Graphics and Vision, Graz University of Technology, Graz, Austria
123 rdf:type schema:Organization
124 grid-institutes:grid.5963.9 schema:alternateName Computer Vision Group, University of Freiburg, Freiburg, Germany
125 schema:name Computer Vision Group, University of Freiburg, Freiburg, Germany
126 rdf:type schema:Organization
 




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


...