FROST—Fast row-stochastic optimization with uncoordinated step-sizes View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2019-12

AUTHORS

Ran Xin, Chenguang Xi, Usman A. Khan

ABSTRACT

In this paper, we discuss distributed optimization over directed graphs, where doubly stochastic weights cannot be constructed. Most of the existing algorithms overcome this issue by applying push-sum consensus, which utilizes column-stochastic weights. The formulation of column-stochastic weights requires each agent to know (at least) its out-degree, which may be impractical in, for example, broadcast-based communication protocols. In contrast, we describe FROST (Fast Row-stochastic-Optimization with uncoordinated STep-sizes), an optimization algorithm applicable to directed graphs that does not require the knowledge of out-degrees, the implementation of which is straightforward as each agent locally assigns weights to the incoming information and locally chooses a suitable step-size. We show that FROST converges linearly to the optimal solution for smooth and strongly convex functions given that the largest step-size is positive and sufficiently small. More... »

PAGES

1

Identifiers

URI

http://scigraph.springernature.com/pub.10.1186/s13634-018-0596-y

DOI

http://dx.doi.org/10.1186/s13634-018-0596-y

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1111411268


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/2008/0103", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Numerical and Computational Mathematics", 
        "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": "Tufts University", 
          "id": "https://www.grid.ac/institutes/grid.429997.8", 
          "name": [
            "Electrical and Computer Engineering, Tufts University, Medford, MA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Xin", 
        "givenName": "Ran", 
        "id": "sg:person.013277062000.61", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013277062000.61"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Facebook (United States)", 
          "id": "https://www.grid.ac/institutes/grid.453567.6", 
          "name": [
            "Electrical and Computer Engineering, Tufts University, Medford, MA, USA", 
            "Facebook Inc., Menlo Park, CA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Xi", 
        "givenName": "Chenguang", 
        "id": "sg:person.016076747103.40", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016076747103.40"
        ], 
        "type": "Person"
      }, 
      {
        "affiliation": {
          "alternateName": "Tufts University", 
          "id": "https://www.grid.ac/institutes/grid.429997.8", 
          "name": [
            "Electrical and Computer Engineering, Tufts University, Medford, MA, USA"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Khan", 
        "givenName": "Usman A.", 
        "id": "sg:person.07542075355.25", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07542075355.25"
        ], 
        "type": "Person"
      }
    ], 
    "citation": [
      {
        "id": "https://doi.org/10.1016/j.automatica.2009.10.021", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1002412828"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.automatica.2012.08.003", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1027659629"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3182/20110828-6-it-1002.01959", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031276146"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1145/1791212.1791218", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1031277802"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1002/nav.3800020109", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1032778056"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neunet.2016.04.007", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1038381988"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/b978-0-12-411597-2.00009-6", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1049804967"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.1986.1104412", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061474635"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2003.812781", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061475326"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2008.2009515", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061476822"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2014.2298712", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061478990"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2014.2364096", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061479339"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2016.2615066", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061480293"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsipn.2016.2524588", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061791473"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2009.2038417", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061801984"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2010.2055862", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061802305"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2012.2232663", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061803649"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2013.2254478", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061803781"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2014.2304432", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061804258"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2015.2472372", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1061805133"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/130943170", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062871459"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/14096668x", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1062872171"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1561/2200000016", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1068001405"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2017.2672698", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1083936435"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tcns.2017.2698261", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1085304177"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.neucom.2017.06.038", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090302919"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2017.2730481", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1090861072"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2017.2737582", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091111621"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.ins.2017.09.038", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1091772470"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.23919/acc.2017.7963560", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093218956"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cdc.2012.6425904", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093609723"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/isit.2010.5513273", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1093815734"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/sfcs.2003.1238221", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1094284548"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/acssc.2016.7869154", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095458774"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/acc.2016.7526803", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095795408"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/cdc.2012.6426375", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1095816870"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1137/16m1084316", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1099939911"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tac.2018.2797164", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1100609790"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/lcsys.2018.2834316", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1103891956"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/jproc.2018.2823638", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1104218739"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2018.2875898", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107651962"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1109/tsp.2018.2875898", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1107651962"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "datePublished": "2019-12", 
    "datePublishedReg": "2019-12-01", 
    "description": "In this paper, we discuss distributed optimization over directed graphs, where doubly stochastic weights cannot be constructed. Most of the existing algorithms overcome this issue by applying push-sum consensus, which utilizes column-stochastic weights. The formulation of column-stochastic weights requires each agent to know (at least) its out-degree, which may be impractical in, for example, broadcast-based communication protocols. In contrast, we describe FROST (Fast Row-stochastic-Optimization with uncoordinated STep-sizes), an optimization algorithm applicable to directed graphs that does not require the knowledge of out-degrees, the implementation of which is straightforward as each agent locally assigns weights to the incoming information and locally chooses a suitable step-size. We show that FROST converges linearly to the optimal solution for smooth and strongly convex functions given that the largest step-size is positive and sufficiently small.", 
    "genre": "research_article", 
    "id": "sg:pub.10.1186/s13634-018-0596-y", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isFundedItemOf": [
      {
        "id": "sg:grant.3490357", 
        "type": "MonetaryGrant"
      }
    ], 
    "isPartOf": [
      {
        "id": "sg:journal.1357355", 
        "issn": [
          "1687-6172", 
          "1687-0433"
        ], 
        "name": "Applied Signal Processing", 
        "type": "Periodical"
      }, 
      {
        "issueNumber": "1", 
        "type": "PublicationIssue"
      }, 
      {
        "type": "PublicationVolume", 
        "volumeNumber": "2019"
      }
    ], 
    "name": "FROST\u2014Fast row-stochastic optimization with uncoordinated step-sizes", 
    "pagination": "1", 
    "productId": [
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "d172c7a77b4171886b9afe3dbe4b85108613983937ea3757c4e1f9b917566e04"
        ]
      }, 
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1186/s13634-018-0596-y"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1111411268"
        ]
      }
    ], 
    "sameAs": [
      "https://doi.org/10.1186/s13634-018-0596-y", 
      "https://app.dimensions.ai/details/publication/pub.1111411268"
    ], 
    "sdDataset": "articles", 
    "sdDatePublished": "2019-04-11T08:40", 
    "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/v90/0000000319_0000000319/records_11214_00000000.jsonl", 
    "type": "ScholarlyArticle", 
    "url": "https://link.springer.com/10.1186%2Fs13634-018-0596-y"
  }
]
 

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.10.1186/s13634-018-0596-y'

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

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13634-018-0596-y'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13634-018-0596-y'

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

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13634-018-0596-y'


 

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

204 TRIPLES      21 PREDICATES      68 URIs      19 LITERALS      7 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1186/s13634-018-0596-y schema:about anzsrc-for:01
2 anzsrc-for:0103
3 schema:author N3ace481f08be4350af7d2b0348124c92
4 schema:citation https://doi.org/10.1002/nav.3800020109
5 https://doi.org/10.1016/b978-0-12-411597-2.00009-6
6 https://doi.org/10.1016/j.automatica.2009.10.021
7 https://doi.org/10.1016/j.automatica.2012.08.003
8 https://doi.org/10.1016/j.ins.2017.09.038
9 https://doi.org/10.1016/j.neucom.2017.06.038
10 https://doi.org/10.1016/j.neunet.2016.04.007
11 https://doi.org/10.1109/acc.2016.7526803
12 https://doi.org/10.1109/acssc.2016.7869154
13 https://doi.org/10.1109/cdc.2012.6425904
14 https://doi.org/10.1109/cdc.2012.6426375
15 https://doi.org/10.1109/isit.2010.5513273
16 https://doi.org/10.1109/jproc.2018.2823638
17 https://doi.org/10.1109/lcsys.2018.2834316
18 https://doi.org/10.1109/sfcs.2003.1238221
19 https://doi.org/10.1109/tac.1986.1104412
20 https://doi.org/10.1109/tac.2003.812781
21 https://doi.org/10.1109/tac.2008.2009515
22 https://doi.org/10.1109/tac.2014.2298712
23 https://doi.org/10.1109/tac.2014.2364096
24 https://doi.org/10.1109/tac.2016.2615066
25 https://doi.org/10.1109/tac.2017.2672698
26 https://doi.org/10.1109/tac.2017.2730481
27 https://doi.org/10.1109/tac.2017.2737582
28 https://doi.org/10.1109/tac.2018.2797164
29 https://doi.org/10.1109/tcns.2017.2698261
30 https://doi.org/10.1109/tsipn.2016.2524588
31 https://doi.org/10.1109/tsp.2009.2038417
32 https://doi.org/10.1109/tsp.2010.2055862
33 https://doi.org/10.1109/tsp.2012.2232663
34 https://doi.org/10.1109/tsp.2013.2254478
35 https://doi.org/10.1109/tsp.2014.2304432
36 https://doi.org/10.1109/tsp.2015.2472372
37 https://doi.org/10.1109/tsp.2018.2875898
38 https://doi.org/10.1137/130943170
39 https://doi.org/10.1137/14096668x
40 https://doi.org/10.1137/16m1084316
41 https://doi.org/10.1145/1791212.1791218
42 https://doi.org/10.1561/2200000016
43 https://doi.org/10.23919/acc.2017.7963560
44 https://doi.org/10.3182/20110828-6-it-1002.01959
45 schema:datePublished 2019-12
46 schema:datePublishedReg 2019-12-01
47 schema:description In this paper, we discuss distributed optimization over directed graphs, where doubly stochastic weights cannot be constructed. Most of the existing algorithms overcome this issue by applying push-sum consensus, which utilizes column-stochastic weights. The formulation of column-stochastic weights requires each agent to know (at least) its out-degree, which may be impractical in, for example, broadcast-based communication protocols. In contrast, we describe FROST (Fast Row-stochastic-Optimization with uncoordinated STep-sizes), an optimization algorithm applicable to directed graphs that does not require the knowledge of out-degrees, the implementation of which is straightforward as each agent locally assigns weights to the incoming information and locally chooses a suitable step-size. We show that FROST converges linearly to the optimal solution for smooth and strongly convex functions given that the largest step-size is positive and sufficiently small.
48 schema:genre research_article
49 schema:inLanguage en
50 schema:isAccessibleForFree true
51 schema:isPartOf N2d384340fa8d4fab9c20de86ab107180
52 N5e38953a19f9470daddedd434f058682
53 sg:journal.1357355
54 schema:name FROST—Fast row-stochastic optimization with uncoordinated step-sizes
55 schema:pagination 1
56 schema:productId N4b278d0638d742fe9f06313a8fea0463
57 Nc2ff14b8321a43589443de41204c3d9c
58 Ncc39ae334827406caecdfed3c2b2a76a
59 schema:sameAs https://app.dimensions.ai/details/publication/pub.1111411268
60 https://doi.org/10.1186/s13634-018-0596-y
61 schema:sdDatePublished 2019-04-11T08:40
62 schema:sdLicense https://scigraph.springernature.com/explorer/license/
63 schema:sdPublisher N74a6bef554a144c383c5f26363062378
64 schema:url https://link.springer.com/10.1186%2Fs13634-018-0596-y
65 sgo:license sg:explorer/license/
66 sgo:sdDataset articles
67 rdf:type schema:ScholarlyArticle
68 N0d0d5605b1dd487e92b1a777c054ebb2 rdf:first sg:person.07542075355.25
69 rdf:rest rdf:nil
70 N2d384340fa8d4fab9c20de86ab107180 schema:issueNumber 1
71 rdf:type schema:PublicationIssue
72 N3ace481f08be4350af7d2b0348124c92 rdf:first sg:person.013277062000.61
73 rdf:rest N8d124e3b2ff84796a7a62d9c5be9dab6
74 N4b278d0638d742fe9f06313a8fea0463 schema:name doi
75 schema:value 10.1186/s13634-018-0596-y
76 rdf:type schema:PropertyValue
77 N5e38953a19f9470daddedd434f058682 schema:volumeNumber 2019
78 rdf:type schema:PublicationVolume
79 N74a6bef554a144c383c5f26363062378 schema:name Springer Nature - SN SciGraph project
80 rdf:type schema:Organization
81 N8d124e3b2ff84796a7a62d9c5be9dab6 rdf:first sg:person.016076747103.40
82 rdf:rest N0d0d5605b1dd487e92b1a777c054ebb2
83 Nc2ff14b8321a43589443de41204c3d9c schema:name readcube_id
84 schema:value d172c7a77b4171886b9afe3dbe4b85108613983937ea3757c4e1f9b917566e04
85 rdf:type schema:PropertyValue
86 Ncc39ae334827406caecdfed3c2b2a76a schema:name dimensions_id
87 schema:value pub.1111411268
88 rdf:type schema:PropertyValue
89 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
90 schema:name Mathematical Sciences
91 rdf:type schema:DefinedTerm
92 anzsrc-for:0103 schema:inDefinedTermSet anzsrc-for:
93 schema:name Numerical and Computational Mathematics
94 rdf:type schema:DefinedTerm
95 sg:grant.3490357 http://pending.schema.org/fundedItem sg:pub.10.1186/s13634-018-0596-y
96 rdf:type schema:MonetaryGrant
97 sg:journal.1357355 schema:issn 1687-0433
98 1687-6172
99 schema:name Applied Signal Processing
100 rdf:type schema:Periodical
101 sg:person.013277062000.61 schema:affiliation https://www.grid.ac/institutes/grid.429997.8
102 schema:familyName Xin
103 schema:givenName Ran
104 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013277062000.61
105 rdf:type schema:Person
106 sg:person.016076747103.40 schema:affiliation https://www.grid.ac/institutes/grid.453567.6
107 schema:familyName Xi
108 schema:givenName Chenguang
109 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016076747103.40
110 rdf:type schema:Person
111 sg:person.07542075355.25 schema:affiliation https://www.grid.ac/institutes/grid.429997.8
112 schema:familyName Khan
113 schema:givenName Usman A.
114 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.07542075355.25
115 rdf:type schema:Person
116 https://doi.org/10.1002/nav.3800020109 schema:sameAs https://app.dimensions.ai/details/publication/pub.1032778056
117 rdf:type schema:CreativeWork
118 https://doi.org/10.1016/b978-0-12-411597-2.00009-6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1049804967
119 rdf:type schema:CreativeWork
120 https://doi.org/10.1016/j.automatica.2009.10.021 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002412828
121 rdf:type schema:CreativeWork
122 https://doi.org/10.1016/j.automatica.2012.08.003 schema:sameAs https://app.dimensions.ai/details/publication/pub.1027659629
123 rdf:type schema:CreativeWork
124 https://doi.org/10.1016/j.ins.2017.09.038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091772470
125 rdf:type schema:CreativeWork
126 https://doi.org/10.1016/j.neucom.2017.06.038 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090302919
127 rdf:type schema:CreativeWork
128 https://doi.org/10.1016/j.neunet.2016.04.007 schema:sameAs https://app.dimensions.ai/details/publication/pub.1038381988
129 rdf:type schema:CreativeWork
130 https://doi.org/10.1109/acc.2016.7526803 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095795408
131 rdf:type schema:CreativeWork
132 https://doi.org/10.1109/acssc.2016.7869154 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095458774
133 rdf:type schema:CreativeWork
134 https://doi.org/10.1109/cdc.2012.6425904 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093609723
135 rdf:type schema:CreativeWork
136 https://doi.org/10.1109/cdc.2012.6426375 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095816870
137 rdf:type schema:CreativeWork
138 https://doi.org/10.1109/isit.2010.5513273 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093815734
139 rdf:type schema:CreativeWork
140 https://doi.org/10.1109/jproc.2018.2823638 schema:sameAs https://app.dimensions.ai/details/publication/pub.1104218739
141 rdf:type schema:CreativeWork
142 https://doi.org/10.1109/lcsys.2018.2834316 schema:sameAs https://app.dimensions.ai/details/publication/pub.1103891956
143 rdf:type schema:CreativeWork
144 https://doi.org/10.1109/sfcs.2003.1238221 schema:sameAs https://app.dimensions.ai/details/publication/pub.1094284548
145 rdf:type schema:CreativeWork
146 https://doi.org/10.1109/tac.1986.1104412 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061474635
147 rdf:type schema:CreativeWork
148 https://doi.org/10.1109/tac.2003.812781 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061475326
149 rdf:type schema:CreativeWork
150 https://doi.org/10.1109/tac.2008.2009515 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061476822
151 rdf:type schema:CreativeWork
152 https://doi.org/10.1109/tac.2014.2298712 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061478990
153 rdf:type schema:CreativeWork
154 https://doi.org/10.1109/tac.2014.2364096 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061479339
155 rdf:type schema:CreativeWork
156 https://doi.org/10.1109/tac.2016.2615066 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061480293
157 rdf:type schema:CreativeWork
158 https://doi.org/10.1109/tac.2017.2672698 schema:sameAs https://app.dimensions.ai/details/publication/pub.1083936435
159 rdf:type schema:CreativeWork
160 https://doi.org/10.1109/tac.2017.2730481 schema:sameAs https://app.dimensions.ai/details/publication/pub.1090861072
161 rdf:type schema:CreativeWork
162 https://doi.org/10.1109/tac.2017.2737582 schema:sameAs https://app.dimensions.ai/details/publication/pub.1091111621
163 rdf:type schema:CreativeWork
164 https://doi.org/10.1109/tac.2018.2797164 schema:sameAs https://app.dimensions.ai/details/publication/pub.1100609790
165 rdf:type schema:CreativeWork
166 https://doi.org/10.1109/tcns.2017.2698261 schema:sameAs https://app.dimensions.ai/details/publication/pub.1085304177
167 rdf:type schema:CreativeWork
168 https://doi.org/10.1109/tsipn.2016.2524588 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061791473
169 rdf:type schema:CreativeWork
170 https://doi.org/10.1109/tsp.2009.2038417 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061801984
171 rdf:type schema:CreativeWork
172 https://doi.org/10.1109/tsp.2010.2055862 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061802305
173 rdf:type schema:CreativeWork
174 https://doi.org/10.1109/tsp.2012.2232663 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061803649
175 rdf:type schema:CreativeWork
176 https://doi.org/10.1109/tsp.2013.2254478 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061803781
177 rdf:type schema:CreativeWork
178 https://doi.org/10.1109/tsp.2014.2304432 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061804258
179 rdf:type schema:CreativeWork
180 https://doi.org/10.1109/tsp.2015.2472372 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061805133
181 rdf:type schema:CreativeWork
182 https://doi.org/10.1109/tsp.2018.2875898 schema:sameAs https://app.dimensions.ai/details/publication/pub.1107651962
183 rdf:type schema:CreativeWork
184 https://doi.org/10.1137/130943170 schema:sameAs https://app.dimensions.ai/details/publication/pub.1062871459
185 rdf:type schema:CreativeWork
186 https://doi.org/10.1137/14096668x schema:sameAs https://app.dimensions.ai/details/publication/pub.1062872171
187 rdf:type schema:CreativeWork
188 https://doi.org/10.1137/16m1084316 schema:sameAs https://app.dimensions.ai/details/publication/pub.1099939911
189 rdf:type schema:CreativeWork
190 https://doi.org/10.1145/1791212.1791218 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031277802
191 rdf:type schema:CreativeWork
192 https://doi.org/10.1561/2200000016 schema:sameAs https://app.dimensions.ai/details/publication/pub.1068001405
193 rdf:type schema:CreativeWork
194 https://doi.org/10.23919/acc.2017.7963560 schema:sameAs https://app.dimensions.ai/details/publication/pub.1093218956
195 rdf:type schema:CreativeWork
196 https://doi.org/10.3182/20110828-6-it-1002.01959 schema:sameAs https://app.dimensions.ai/details/publication/pub.1031276146
197 rdf:type schema:CreativeWork
198 https://www.grid.ac/institutes/grid.429997.8 schema:alternateName Tufts University
199 schema:name Electrical and Computer Engineering, Tufts University, Medford, MA, USA
200 rdf:type schema:Organization
201 https://www.grid.ac/institutes/grid.453567.6 schema:alternateName Facebook (United States)
202 schema:name Electrical and Computer Engineering, Tufts University, Medford, MA, USA
203 Facebook Inc., Menlo Park, CA, USA
204 rdf:type schema:Organization
 




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


...