CAREER: Machine Learning Theory with Connections to Algorithmic Game Theory and Combinatorial Optimization View Homepage


Ontology type: schema:MonetaryGrant     


Grant Info

YEARS

2009-2014

FUNDING AMOUNT

400000 USD

ABSTRACT

Over the years, Machine Learning has become a very broad discipline with important applications to many areas including computer vision, speech recognition, robotics, and bio-surveillance, to name just a few. Moreover, many of these application areas have faced a huge increase in the volume of available data of various kinds. In order to be able to use all this data a number of new learning approaches have been proposed. These approaches have been intensely explored in the machine learning community, with many heuristics and specific algorithms, as well as experimental results reported. Unfortunately, however, the standard theoretical models do not capture the key issues involved in these learning techniques, and it has become clear that for developing robust, versatile, and general algorithms in these settings a more fundamental understanding is necessary. This project will develop theoretical foundations for such learning paradigms which are of significant practical importance but are not explained by existing theoretical models. This project will also develop fundamental new connections between Machine Learning, Game Theory, and Combinatorial Optimization, that will aid in advancing and solving important problems in all three areas. The key research directions of this project are: 1. Developing mathematical foundations and algorithms for important machine learning paradigms that are not captured well by standard models. This includes new analysis frameworks as well as new practical and theoretically justified algorithms both for semi-supervised learning and active learning, two important emerging approaches for incorporating unlabeled data and interaction in the learning process. This project will also explore a fundamentally new approach to analyzing clustering -- a classic central task in the analysis and exploration of data, for which the existing theory has been very brittle. This framework will enable practitioners to describe in a formal way the properties they believe to be true about their data, and then use these properties to choose or design the right algorithm for their needs. 2. Developing novel fundamental connections between Machine Learning and Algorithmic Game Theory in order to solve difficult problems in multi-agent systems that have resisted previous approaches. In particular, many multi-agent interactions have bad equilibria, and it is important to develop methods for helping agents in such bad states to move to better ones. This project will develop techniques for understanding and influencing the behavior of natural dynamics in games of this type, by using connections to important concepts in Machine Learning, such as learning from untrusted experts' advice. 3. Developing fundamental connections between Machine Learning and Combinatorial Optimization in order to advance both areas. These include new connections between approximation algorithms and learning-based objectives for clustering, and new algorithms and computational theory for learning submodular functions. Submodular functions, which describe laws of diminishing returns, are ubiquitous in economic optimization problems, and methods for learning them from observed data can aid in designing improved decision procedures. Altogether, this project will advance Machine Learning, Algorithmic Game Theory, and Combinatorial Optimization, by developing and exploiting novel connections between these areas. The theory developed by this work will enable the next generation of powerful algorithms for machine learning and multi-agent systems. It will additionally impact a wide range of application areas including computer vision, robotics, bio-surveillance, and online auction design. More broadly, the research results of this project will have impact across a number of scientific, medical, and industrial fields. The PI's education plan further contributes to the project's impact. In addition to advising a diverse set of students on projects directly related to this project, the progress in this research will be used to influence the curriculum via special courses presenting the theoretical advances along with their applications. The PI will also contribute to increasing the participation of women in computational sciences. More... »

URL

http://www.nsf.gov/awardsearch/showAward?AWD_ID=0953192&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/2008/2201", 
        "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"
      }, 
      {
        "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": "400000"
    }, 
    "description": "Over the years, Machine Learning has become a very broad discipline with important applications to many areas including computer vision, speech recognition, robotics, and bio-surveillance, to name just a few. Moreover, many of these application areas have faced a huge increase in the volume of available data of various kinds. In order to be able to use all this data a number of new learning approaches have been proposed. These approaches have been intensely explored in the machine learning community, with many heuristics and specific algorithms, as well as experimental results reported. Unfortunately, however, the standard theoretical models do not capture the key issues involved in these learning techniques, and it has become clear that for developing robust, versatile, and general algorithms in these settings a more fundamental understanding is necessary. This project will develop theoretical foundations for such learning paradigms which are of significant practical importance but are not explained by existing theoretical models. This project will also develop fundamental new connections between Machine Learning, Game Theory, and Combinatorial Optimization, that will aid in advancing and solving important problems in all three areas. The key research directions of this project are: 1. Developing mathematical foundations and algorithms for important machine learning paradigms that are not captured well by standard models. This includes new analysis frameworks as well as new practical and theoretically justified algorithms both for semi-supervised learning and active learning, two important emerging approaches for incorporating unlabeled data and interaction in the learning process. This project will also explore a fundamentally new approach to analyzing clustering -- a classic central task in the analysis and exploration of data, for which the existing theory has been very brittle. This framework will enable practitioners to describe in a formal way the properties they believe to be true about their data, and then use these properties to choose or design the right algorithm for their needs. 2. Developing novel fundamental connections between Machine Learning and Algorithmic Game Theory in order to solve difficult problems in multi-agent systems that have resisted previous approaches. In particular, many multi-agent interactions have bad equilibria, and it is important to develop methods for helping agents in such bad states to move to better ones. This project will develop techniques for understanding and influencing the behavior of natural dynamics in games of this type, by using connections to important concepts in Machine Learning, such as learning from untrusted experts' advice. 3. Developing fundamental connections between Machine Learning and Combinatorial Optimization in order to advance both areas. These include new connections between approximation algorithms and learning-based objectives for clustering, and new algorithms and computational theory for learning submodular functions. Submodular functions, which describe laws of diminishing returns, are ubiquitous in economic optimization problems, and methods for learning them from observed data can aid in designing improved decision procedures. Altogether, this project will advance Machine Learning, Algorithmic Game Theory, and Combinatorial Optimization, by developing and exploiting novel connections between these areas. The theory developed by this work will enable the next generation of powerful algorithms for machine learning and multi-agent systems. It will additionally impact a wide range of application areas including computer vision, robotics, bio-surveillance, and online auction design. More broadly, the research results of this project will have impact across a number of scientific, medical, and industrial fields. The PI's education plan further contributes to the project's impact. In addition to advising a diverse set of students on projects directly related to this project, the progress in this research will be used to influence the curriculum via special courses presenting the theoretical advances along with their applications. The PI will also contribute to increasing the participation of women in computational sciences.", 
    "endDate": "2014-10-31T00:00:00Z", 
    "funder": {
      "id": "https://www.grid.ac/institutes/grid.457785.c", 
      "type": "Organization"
    }, 
    "id": "sg:grant.2998812", 
    "identifier": [
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "2998812"
        ]
      }, 
      {
        "name": "nsf_id", 
        "type": "PropertyValue", 
        "value": [
          "0953192"
        ]
      }
    ], 
    "inLanguage": [
      "en"
    ], 
    "keywords": [
      "economic optimization problem", 
      "next generation", 
      "paradigms", 
      "need", 
      "powerful algorithms", 
      "industrial fields", 
      "improved decision procedures", 
      "general algorithms", 
      "classic central task", 
      "active learning", 
      "properties", 
      "huge increase", 
      "experimental results", 
      "learning", 
      "type", 
      "theoretical model", 
      "standard model", 
      "theoretical foundation", 
      "Pi", 
      "progress", 
      "theoretical advances", 
      "important machine", 
      "project impacts", 
      "key issues", 
      "application areas", 
      "addition", 
      "novel connection", 
      "fundamental connection", 
      "fundamental understanding", 
      "machine learning theory", 
      "novel", 
      "data", 
      "participation", 
      "students", 
      "combinatorial optimization", 
      "unlabeled data", 
      "work", 
      "volume", 
      "various kinds", 
      "return", 
      "significant practical importance", 
      "SETTING", 
      "right algorithm", 
      "untrusted experts' advice", 
      "many areas", 
      "wide range", 
      "clustering", 
      "learning-based objectives", 
      "mathematical foundations", 
      "online auction design", 
      "order", 
      "new learning approach", 
      "important problem", 
      "research", 
      "game", 
      "machine", 
      "natural dynamics", 
      "learning techniques", 
      "agents", 
      "new connections", 
      "curriculum", 
      "bad equilibria", 
      "PI's education plan", 
      "new analysis framework", 
      "area", 
      "important concepts", 
      "machine learning", 
      "multi-agent systems", 
      "new approach", 
      "such bad states", 
      "exploration", 
      "impact", 
      "computational theory", 
      "framework", 
      "special courses", 
      "data", 
      "Connections", 
      "such learning paradigms", 
      "key research directions", 
      "approximation algorithm", 
      "specific algorithms", 
      "career", 
      "community", 
      "computational science", 
      "law", 
      "speech recognition", 
      "important applications", 
      "fundamental new connections", 
      "project", 
      "research results", 
      "formal way", 
      "connection", 
      "good one", 
      "game theory", 
      "many multi-agent interactions", 
      "standard theoretical models", 
      "surveillance", 
      "interaction", 
      "approach", 
      "analysis", 
      "submodular functions", 
      "difficult problem", 
      "algorithmic game theory", 
      "number", 
      "algorithms", 
      "technique", 
      "previous approaches", 
      "new algorithms", 
      "women", 
      "broad discipline", 
      "METHODS", 
      "years", 
      "available data", 
      "computer vision", 
      "semi", 
      "application", 
      "theory", 
      "robotics", 
      "many heuristics", 
      "diverse set", 
      "understanding", 
      "behavior", 
      "learning process", 
      "practitioners"
    ], 
    "name": "CAREER: Machine Learning Theory with Connections to Algorithmic Game Theory and Combinatorial Optimization", 
    "recipient": [
      {
        "id": "https://www.grid.ac/institutes/grid.213917.f", 
        "type": "Organization"
      }, 
      {
        "affiliation": {
          "id": "https://www.grid.ac/institutes/grid.213917.f", 
          "name": "Georgia Tech Research Corporation", 
          "type": "Organization"
        }, 
        "familyName": "Balcan", 
        "givenName": "Maria-Florina", 
        "id": "sg:person.010434121334.35", 
        "type": "Person"
      }, 
      {
        "member": "sg:person.010434121334.35", 
        "roleName": "PI", 
        "type": "Role"
      }
    ], 
    "sameAs": [
      "https://app.dimensions.ai/details/grant/grant.2998812"
    ], 
    "sdDataset": "grants", 
    "sdDatePublished": "2019-03-07T12:34", 
    "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_4.xml.gz", 
    "startDate": "2009-12-01T00:00:00Z", 
    "type": "MonetaryGrant", 
    "url": "http://www.nsf.gov/awardsearch/showAward?AWD_ID=0953192&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.2998812'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/grant.2998812'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/grant.2998812'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/grant.2998812'


 

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

170 TRIPLES      19 PREDICATES      146 URIs      137 LITERALS      5 BLANK NODES

Subject Predicate Object
1 sg:grant.2998812 schema:about anzsrc-for:2201
2 anzsrc-for:2208
3 schema:amount N6c53805cb5354429b273718b34ae3c6a
4 schema:description Over the years, Machine Learning has become a very broad discipline with important applications to many areas including computer vision, speech recognition, robotics, and bio-surveillance, to name just a few. Moreover, many of these application areas have faced a huge increase in the volume of available data of various kinds. In order to be able to use all this data a number of new learning approaches have been proposed. These approaches have been intensely explored in the machine learning community, with many heuristics and specific algorithms, as well as experimental results reported. Unfortunately, however, the standard theoretical models do not capture the key issues involved in these learning techniques, and it has become clear that for developing robust, versatile, and general algorithms in these settings a more fundamental understanding is necessary. This project will develop theoretical foundations for such learning paradigms which are of significant practical importance but are not explained by existing theoretical models. This project will also develop fundamental new connections between Machine Learning, Game Theory, and Combinatorial Optimization, that will aid in advancing and solving important problems in all three areas. The key research directions of this project are: 1. Developing mathematical foundations and algorithms for important machine learning paradigms that are not captured well by standard models. This includes new analysis frameworks as well as new practical and theoretically justified algorithms both for semi-supervised learning and active learning, two important emerging approaches for incorporating unlabeled data and interaction in the learning process. This project will also explore a fundamentally new approach to analyzing clustering -- a classic central task in the analysis and exploration of data, for which the existing theory has been very brittle. This framework will enable practitioners to describe in a formal way the properties they believe to be true about their data, and then use these properties to choose or design the right algorithm for their needs. 2. Developing novel fundamental connections between Machine Learning and Algorithmic Game Theory in order to solve difficult problems in multi-agent systems that have resisted previous approaches. In particular, many multi-agent interactions have bad equilibria, and it is important to develop methods for helping agents in such bad states to move to better ones. This project will develop techniques for understanding and influencing the behavior of natural dynamics in games of this type, by using connections to important concepts in Machine Learning, such as learning from untrusted experts' advice. 3. Developing fundamental connections between Machine Learning and Combinatorial Optimization in order to advance both areas. These include new connections between approximation algorithms and learning-based objectives for clustering, and new algorithms and computational theory for learning submodular functions. Submodular functions, which describe laws of diminishing returns, are ubiquitous in economic optimization problems, and methods for learning them from observed data can aid in designing improved decision procedures. Altogether, this project will advance Machine Learning, Algorithmic Game Theory, and Combinatorial Optimization, by developing and exploiting novel connections between these areas. The theory developed by this work will enable the next generation of powerful algorithms for machine learning and multi-agent systems. It will additionally impact a wide range of application areas including computer vision, robotics, bio-surveillance, and online auction design. More broadly, the research results of this project will have impact across a number of scientific, medical, and industrial fields. The PI's education plan further contributes to the project's impact. In addition to advising a diverse set of students on projects directly related to this project, the progress in this research will be used to influence the curriculum via special courses presenting the theoretical advances along with their applications. The PI will also contribute to increasing the participation of women in computational sciences.
5 schema:endDate 2014-10-31T00:00:00Z
6 schema:funder https://www.grid.ac/institutes/grid.457785.c
7 schema:identifier N03612fb397154c1b9c39ef263277c923
8 N163708a868734cacada306edfff51200
9 schema:inLanguage en
10 schema:keywords Connections
11 METHODS
12 PI's education plan
13 Pi
14 SETTING
15 active learning
16 addition
17 agents
18 algorithmic game theory
19 algorithms
20 analysis
21 application
22 application areas
23 approach
24 approximation algorithm
25 area
26 available data
27 bad equilibria
28 behavior
29 broad discipline
30 career
31 classic central task
32 clustering
33 combinatorial optimization
34 community
35 computational science
36 computational theory
37 computer vision
38 connection
39 curriculum
40 data
41 difficult problem
42 diverse set
43 economic optimization problem
44 experimental results
45 exploration
46 formal way
47 framework
48 fundamental connection
49 fundamental new connections
50 fundamental understanding
51 game
52 game theory
53 general algorithms
54 good one
55 huge increase
56 impact
57 important applications
58 important concepts
59 important machine
60 important problem
61 improved decision procedures
62 industrial fields
63 interaction
64 key issues
65 key research directions
66 law
67 learning
68 learning process
69 learning techniques
70 learning-based objectives
71 machine
72 machine learning
73 machine learning theory
74 many areas
75 many heuristics
76 many multi-agent interactions
77 mathematical foundations
78 multi-agent systems
79 natural dynamics
80 need
81 new algorithms
82 new analysis framework
83 new approach
84 new connections
85 new learning approach
86 next generation
87 novel
88 novel connection
89 number
90 online auction design
91 order
92 paradigms
93 participation
94 powerful algorithms
95 practitioners
96 previous approaches
97 progress
98 project
99 project impacts
100 properties
101 research
102 research results
103 return
104 right algorithm
105 robotics
106 semi
107 significant practical importance
108 special courses
109 specific algorithms
110 speech recognition
111 standard model
112 standard theoretical models
113 students
114 submodular functions
115 such bad states
116 such learning paradigms
117 surveillance
118 technique
119 theoretical advances
120 theoretical foundation
121 theoretical model
122 theory
123 type
124 understanding
125 unlabeled data
126 untrusted experts' advice
127 various kinds
128 volume
129 wide range
130 women
131 work
132 years
133 schema:name CAREER: Machine Learning Theory with Connections to Algorithmic Game Theory and Combinatorial Optimization
134 schema:recipient N7927b6b2d27e44749f5a2d6537d47f70
135 sg:person.010434121334.35
136 https://www.grid.ac/institutes/grid.213917.f
137 schema:sameAs https://app.dimensions.ai/details/grant/grant.2998812
138 schema:sdDatePublished 2019-03-07T12:34
139 schema:sdLicense https://scigraph.springernature.com/explorer/license/
140 schema:sdPublisher N1e93705e91b248df92e00d5c0a292358
141 schema:startDate 2009-12-01T00:00:00Z
142 schema:url http://www.nsf.gov/awardsearch/showAward?AWD_ID=0953192&HistoricalAwards=false
143 sgo:license sg:explorer/license/
144 sgo:sdDataset grants
145 rdf:type schema:MonetaryGrant
146 N03612fb397154c1b9c39ef263277c923 schema:name nsf_id
147 schema:value 0953192
148 rdf:type schema:PropertyValue
149 N163708a868734cacada306edfff51200 schema:name dimensions_id
150 schema:value 2998812
151 rdf:type schema:PropertyValue
152 N1e93705e91b248df92e00d5c0a292358 schema:name Springer Nature - SN SciGraph project
153 rdf:type schema:Organization
154 N6c53805cb5354429b273718b34ae3c6a schema:currency USD
155 schema:value 400000
156 rdf:type schema:MonetaryAmount
157 N7927b6b2d27e44749f5a2d6537d47f70 schema:member sg:person.010434121334.35
158 schema:roleName PI
159 rdf:type schema:Role
160 anzsrc-for:2201 schema:inDefinedTermSet anzsrc-for:
161 rdf:type schema:DefinedTerm
162 anzsrc-for:2208 schema:inDefinedTermSet anzsrc-for:
163 rdf:type schema:DefinedTerm
164 sg:person.010434121334.35 schema:affiliation https://www.grid.ac/institutes/grid.213917.f
165 schema:familyName Balcan
166 schema:givenName Maria-Florina
167 rdf:type schema:Person
168 https://www.grid.ac/institutes/grid.213917.f schema:name Georgia Tech Research Corporation
169 rdf:type schema:Organization
170 https://www.grid.ac/institutes/grid.457785.c schema:Organization
 




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


...