RI: Medium: Advances and Applications in Submodularity for Machine Learning View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2012-2018

FUNDING AMOUNT

814509 USD

ABSTRACT

Submodularity is an intuitive diminishing returns property, stating that adding an element to a smaller set helps more than adding it to a larger set. Submodularity allows one to efficiently find provably optimal or near-optimal solutions to discrete problems. Submodular minimization has found use, e.g., in graphical model inference and clustering, whereas maximization has been applied, e.g., to variable/feature selection and active learning. Submodularity, however, is still only beginning to show applicability in machine learning and its applications. Moreover, work on submodular optimization in the combinatorics and operations research literature has been primarily unaware of unique problems arising in machine learning. Therefore, existing standard algorithms do not exploit certain structures or variants of the submodular problems arising in machine learning. Studying novel machine learning problems involving submodular objectives can thus lead to advances in the pure combinatorics literature. We propose to pursue activities that bring together research in machine learning and combinatorial optimization to solve problems which neither of the communities can solve alone. In particular, we propose to use insights from machine learning to enable scaling up typical submodular optimization problem sizes (by focusing on problem instances arising in learning). We also propose to further chart the territory that submodularity plays in machine learning. In this grant, we will introduce new submodular structures specifically related to submodularity. We will introduce submodular learning problems for machine learning. We will introduce new submodular optimization problems with constraints. And lastly, we will apply these submodular instances to real-world applications in computer vision, speech recognition, and natural language processing. More... »

URL

http://www.nsf.gov/awardsearch/showAward?AWD_ID=1162606&HistoricalAwards=false

Related SciGraph Publications

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/2008/2217", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2201", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2208", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "amount": {
      "currency": "USD", 
      "type": "MonetaryAmount", 
      "value": "814509"
    }, 
    "description": "Submodularity is an intuitive diminishing returns property, stating that adding an element to a smaller set helps more than adding it to a larger set. Submodularity allows one to efficiently find provably optimal or near-optimal solutions to discrete problems. Submodular minimization has found use, e.g., in graphical model inference and clustering, whereas maximization has been applied, e.g., to variable/feature selection and active learning. Submodularity, however, is still only beginning to show applicability in machine learning and its applications. Moreover, work on submodular optimization in the combinatorics and operations research literature has been primarily unaware of unique problems arising in machine learning. Therefore, existing standard algorithms do not exploit certain structures or variants of the submodular problems arising in machine learning. Studying novel machine learning problems involving submodular objectives can thus lead to advances in the pure combinatorics literature. We propose to pursue activities that bring together research in machine learning and combinatorial optimization to solve problems which neither of the communities can solve alone. In particular, we propose to use insights from machine learning to enable scaling up typical submodular optimization problem sizes (by focusing on problem instances arising in learning). We also propose to further chart the territory that submodularity plays in machine learning. In this grant, we will introduce new submodular structures specifically related to submodularity. We will introduce submodular learning problems for machine learning. We will introduce new submodular optimization problems with constraints. And lastly, we will apply these submodular instances to real-world applications in computer vision, speech recognition, and natural language processing.", 
    "endDate": "2018-06-30T00:00:00Z", 
    "funder": {
      "id": "https://www.grid.ac/institutes/grid.457785.c", 
      "type": "Organization"
    }, 
    "id": "sg:grant.3133903", 
    "identifier": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "3133903"
        ]
      }, 
      {
        "name": "nsf_id", 
        "type": "PropertyValue", 
        "value": [
          "1162606"
        ]
      }
    ], 
    "inLanguage": [
      "en"
    ], 
    "keywords": [
      "submodular minimization", 
      "problem instances", 
      "submodular instances", 
      "constraints", 
      "use", 
      "active learning", 
      "new submodular structures", 
      "problem", 
      "elements", 
      "intuitive diminishing returns property", 
      "graphical model inference", 
      "small set", 
      "discrete problem", 
      "learning", 
      "certain structures", 
      "maximization", 
      "feature selection", 
      "submodular optimization", 
      "work", 
      "medium", 
      "natural language processing", 
      "unique problems", 
      "standard algorithm", 
      "near-optimal solution", 
      "operations research literature", 
      "real-world applications", 
      "submodularity", 
      "research", 
      "speech recognition", 
      "variants", 
      "activity", 
      "new submodular optimization problems", 
      "pure combinatorics literature", 
      "submodular problems", 
      "machine learning", 
      "advances", 
      "combinatorial optimization", 
      "applicability", 
      "community", 
      "territory", 
      "combinatorics", 
      "insight", 
      "typical submodular optimization problem", 
      "submodular objectives", 
      "large set", 
      "machine", 
      "submodular learning problems", 
      "grant", 
      "clustering", 
      "application", 
      "computer vision", 
      "novel machine learning problems", 
      "RI"
    ], 
    "name": "RI: Medium: Advances and Applications in Submodularity for Machine Learning", 
    "recipient": [
      {
        "id": "https://www.grid.ac/institutes/grid.34477.33", 
        "type": "Organization"
      }, 
      {
        "affiliation": {
          "id": "https://www.grid.ac/institutes/grid.34477.33", 
          "name": "University of Washington", 
          "type": "Organization"
        }, 
        "familyName": "Bilmes", 
        "givenName": "Jeffrey", 
        "id": "sg:person.01267611704.16", 
        "type": "Person"
      }, 
      {
        "member": "sg:person.01267611704.16", 
        "roleName": "PI", 
        "type": "Role"
      }
    ], 
    "sameAs": [
      "https://app.dimensions.ai/details/grant/grant.3133903"
    ], 
    "sdDataset": "grants", 
    "sdDatePublished": "2019-03-07T12:35", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com.uberresearch.data.processor/core_data/20181219_192338/projects/base/nsf_projects_6.xml.gz", 
    "startDate": "2012-07-01T00:00:00Z", 
    "type": "MonetaryGrant", 
    "url": "http://www.nsf.gov/awardsearch/showAward?AWD_ID=1162606&HistoricalAwards=false"
  }
]
 

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/grant.3133903'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.3133903'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.3133903'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.3133903'


 

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

103 TRIPLES      19 PREDICATES      77 URIs      67 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:grant.3133903 schema:about anzsrc-for:2201
2 anzsrc-for:2208
3 anzsrc-for:2217
4 schema:amount N4e64b38687444231a0c58322caec86c1
5 schema:description Submodularity is an intuitive diminishing returns property, stating that adding an element to a smaller set helps more than adding it to a larger set. Submodularity allows one to efficiently find provably optimal or near-optimal solutions to discrete problems. Submodular minimization has found use, e.g., in graphical model inference and clustering, whereas maximization has been applied, e.g., to variable/feature selection and active learning. Submodularity, however, is still only beginning to show applicability in machine learning and its applications. Moreover, work on submodular optimization in the combinatorics and operations research literature has been primarily unaware of unique problems arising in machine learning. Therefore, existing standard algorithms do not exploit certain structures or variants of the submodular problems arising in machine learning. Studying novel machine learning problems involving submodular objectives can thus lead to advances in the pure combinatorics literature. We propose to pursue activities that bring together research in machine learning and combinatorial optimization to solve problems which neither of the communities can solve alone. In particular, we propose to use insights from machine learning to enable scaling up typical submodular optimization problem sizes (by focusing on problem instances arising in learning). We also propose to further chart the territory that submodularity plays in machine learning. In this grant, we will introduce new submodular structures specifically related to submodularity. We will introduce submodular learning problems for machine learning. We will introduce new submodular optimization problems with constraints. And lastly, we will apply these submodular instances to real-world applications in computer vision, speech recognition, and natural language processing.
6 schema:endDate 2018-06-30T00:00:00Z
7 schema:funder https://www.grid.ac/institutes/grid.457785.c
8 schema:identifier N8f258153d55042b4aeae011bad2094c8
9 N8f44c94b68be453f949c4cb4564e5c19
10 schema:inLanguage en
11 schema:keywords RI
12 active learning
13 activity
14 advances
15 applicability
16 application
17 certain structures
18 clustering
19 combinatorial optimization
20 combinatorics
21 community
22 computer vision
23 constraints
24 discrete problem
25 elements
26 feature selection
27 grant
28 graphical model inference
29 insight
30 intuitive diminishing returns property
31 large set
32 learning
33 machine
34 machine learning
35 maximization
36 medium
37 natural language processing
38 near-optimal solution
39 new submodular optimization problems
40 new submodular structures
41 novel machine learning problems
42 operations research literature
43 problem
44 problem instances
45 pure combinatorics literature
46 real-world applications
47 research
48 small set
49 speech recognition
50 standard algorithm
51 submodular instances
52 submodular learning problems
53 submodular minimization
54 submodular objectives
55 submodular optimization
56 submodular problems
57 submodularity
58 territory
59 typical submodular optimization problem
60 unique problems
61 use
62 variants
63 work
64 schema:name RI: Medium: Advances and Applications in Submodularity for Machine Learning
65 schema:recipient Nde297b8848c6486dbcedc29c1088526c
66 sg:person.01267611704.16
67 https://www.grid.ac/institutes/grid.34477.33
68 schema:sameAs https://app.dimensions.ai/details/grant/grant.3133903
69 schema:sdDatePublished 2019-03-07T12:35
70 schema:sdLicense https://scigraph.springernature.com/explorer/license/
71 schema:sdPublisher N3c0fded0add9408da4ad0099aeee501a
72 schema:startDate 2012-07-01T00:00:00Z
73 schema:url http://www.nsf.gov/awardsearch/showAward?AWD_ID=1162606&HistoricalAwards=false
74 sgo:license sg:explorer/license/
75 sgo:sdDataset grants
76 rdf:type schema:MonetaryGrant
77 N3c0fded0add9408da4ad0099aeee501a schema:name Springer Nature - SN SciGraph project
78 rdf:type schema:Organization
79 N4e64b38687444231a0c58322caec86c1 schema:currency USD
80 schema:value 814509
81 rdf:type schema:MonetaryAmount
82 N8f258153d55042b4aeae011bad2094c8 schema:name dimensions_id
83 schema:value 3133903
84 rdf:type schema:PropertyValue
85 N8f44c94b68be453f949c4cb4564e5c19 schema:name nsf_id
86 schema:value 1162606
87 rdf:type schema:PropertyValue
88 Nde297b8848c6486dbcedc29c1088526c schema:member sg:person.01267611704.16
89 schema:roleName PI
90 rdf:type schema:Role
91 anzsrc-for:2201 schema:inDefinedTermSet anzsrc-for:
92 rdf:type schema:DefinedTerm
93 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
94 rdf:type schema:DefinedTerm
95 anzsrc-for:2217 schema:inDefinedTermSet anzsrc-for:
96 rdf:type schema:DefinedTerm
97 sg:person.01267611704.16 schema:affiliation https://www.grid.ac/institutes/grid.34477.33
98 schema:familyName Bilmes
99 schema:givenName Jeffrey
100 rdf:type schema:Person
101 https://www.grid.ac/institutes/grid.34477.33 schema:name University of Washington
102 rdf:type schema:Organization
103 https://www.grid.ac/institutes/grid.457785.c schema:Organization
 




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


...