Ontology type: schema:ScholarlyArticle Open Access: True
2019-04
AUTHORS ABSTRACTWe consider the high-dimensional inference problem where the signal is a low-rank symmetric matrix which is corrupted by an additive Gaussian noise. Given a probabilistic model for the low-rank matrix, we compute the limit in the large dimension setting for the mutual information between the signal and the observations, as well as the matrix minimum mean squared error, while the rank of the signal remains constant. We also show that our model extends beyond the particular case of additive Gaussian noise and we prove an universality result connecting the community detection problem to our Gaussian framework. We unify and generalize a number of recent works on PCA, sparse PCA, submatrix localization or community detection by computing the information-theoretic limits for these problems in the high noise regime. In addition, we show that the posterior distribution of the signal given the observations is characterized by a parameter of the same dimension as the square of the rank of the signal (i.e. scalar in the case of rank one). This allows to locate precisely the information-theoretic thresholds for the above mentioned problems. Finally, we connect our work with the hard but detectable conjecture in statistical physics. More... »
PAGES1-71
http://scigraph.springernature.com/pub.10.1007/s00440-018-0845-x
DOIhttp://dx.doi.org/10.1007/s00440-018-0845-x
DIMENSIONShttps://app.dimensions.ai/details/publication/pub.1103204637
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/2008/0801",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Artificial Intelligence and Image Processing",
"type": "DefinedTerm"
},
{
"id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08",
"inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/",
"name": "Information and Computing Sciences",
"type": "DefinedTerm"
}
],
"author": [
{
"affiliation": {
"alternateName": "French Institute for Research in Computer Science and Automation",
"id": "https://www.grid.ac/institutes/grid.5328.c",
"name": [
"D\u00e9partement d\u2019informatique de l\u2019ENS, \u00c9cole normale sup\u00e9rieure, CNRS, PSL Research University, 75005, Paris, France",
"Inria, Paris, France"
],
"type": "Organization"
},
"familyName": "Lelarge",
"givenName": "Marc",
"id": "sg:person.016213456237.22",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.016213456237.22"
],
"type": "Person"
},
{
"affiliation": {
"alternateName": "French Institute for Research in Computer Science and Automation",
"id": "https://www.grid.ac/institutes/grid.5328.c",
"name": [
"D\u00e9partement d\u2019informatique de l\u2019ENS, \u00c9cole normale sup\u00e9rieure, CNRS, PSL Research University, 75005, Paris, France",
"Inria, Paris, France"
],
"type": "Organization"
},
"familyName": "Miolane",
"givenName": "L\u00e9o",
"id": "sg:person.010554052127.82",
"sameAs": [
"https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.010554052127.82"
],
"type": "Person"
}
],
"citation": [
{
"id": "sg:pub.10.1007/978-1-4614-6289-7",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1000983571",
"https://doi.org/10.1007/978-1-4614-6289-7"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-1-4614-6289-7",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1000983571",
"https://doi.org/10.1007/978-1-4614-6289-7"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-3-642-22253-5",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1004111194",
"https://doi.org/10.1007/978-3-642-22253-5"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/978-3-642-22253-5",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1004111194",
"https://doi.org/10.1007/978-3-642-22253-5"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s10955-009-9781-6",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1018841306",
"https://doi.org/10.1007/s10955-009-9781-6"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s10955-009-9781-6",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1018841306",
"https://doi.org/10.1007/s10955-009-9781-6"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1016/j.aim.2011.02.007",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1020111192"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1103/physreve.84.066106",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1022276361"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1103/physreve.84.066106",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1022276361"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1111/1468-0262.00296",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1024974292"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s10955-015-1338-2",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1034110432",
"https://doi.org/10.1007/s10955-015-1338-2"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1103/physrevb.68.214403",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1035833199"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1103/physrevb.68.214403",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1035833199"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s00220-002-0773-5",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1040172373",
"https://doi.org/10.1007/s00220-002-0773-5"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s00220-007-0209-3",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1040289210",
"https://doi.org/10.1007/s00220-007-0209-3"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s00220-007-0209-3",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1040289210",
"https://doi.org/10.1007/s00220-007-0209-3"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1080/00018732.2016.1211393",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1041676048"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1088/0305-4470/31/46/006",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1046416720"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1002/ett.1289",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1046664220"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1214/009117905000000233",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1047241984"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1088/0305-4470/32/21/302",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1048199778"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s10107-016-1059-6",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1052920179",
"https://doi.org/10.1007/s10107-016-1059-6"
],
"type": "CreativeWork"
},
{
"id": "sg:pub.10.1007/s10107-016-1059-6",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1052920179",
"https://doi.org/10.1007/s10107-016-1059-6"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1093/imaiai/iaw017",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1059683467"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tit.2005.844072",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061650466"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tit.2009.2030457",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061652462"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tit.2010.2070131",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061652954"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tit.2011.2112231",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061653191"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tit.2011.2174959",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1061653707"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1214/009117906000000575",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1064389361"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1145/3055399.3055420",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1091883863"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/tnse.2017.2758201",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1092035963"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/isit.2016.7541628",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093171472"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/isit.2015.7282733",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093204823"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/isit.2014.6875223",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093339510"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/allerton.2015.7447070",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093374541"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/itw.2016.7606798",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093542327"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/isit.2015.7282642",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093900309"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/isit.2016.7541405",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1093923793"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/isit.2012.6283056",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094012116"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1109/isit.2017.8006706",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1094674171"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1093/acprof:oso/9780199535255.001.0001",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1098728789"
],
"type": "CreativeWork"
},
{
"id": "https://doi.org/10.1093/acprof:oso/9780198509417.001.0001",
"sameAs": [
"https://app.dimensions.ai/details/publication/pub.1098731037"
],
"type": "CreativeWork"
}
],
"datePublished": "2019-04",
"datePublishedReg": "2019-04-01",
"description": "We consider the high-dimensional inference problem where the signal is a low-rank symmetric matrix which is corrupted by an additive Gaussian noise. Given a probabilistic model for the low-rank matrix, we compute the limit in the large dimension setting for the mutual information between the signal and the observations, as well as the matrix minimum mean squared error, while the rank of the signal remains constant. We also show that our model extends beyond the particular case of additive Gaussian noise and we prove an universality result connecting the community detection problem to our Gaussian framework. We unify and generalize a number of recent works on PCA, sparse PCA, submatrix localization or community detection by computing the information-theoretic limits for these problems in the high noise regime. In addition, we show that the posterior distribution of the signal given the observations is characterized by a parameter of the same dimension as the square of the rank of the signal (i.e. scalar in the case of rank one). This allows to locate precisely the information-theoretic thresholds for the above mentioned problems. Finally, we connect our work with the hard but detectable conjecture in statistical physics.",
"genre": "research_article",
"id": "sg:pub.10.1007/s00440-018-0845-x",
"inLanguage": [
"en"
],
"isAccessibleForFree": true,
"isPartOf": [
{
"id": "sg:journal.1053886",
"issn": [
"0178-8051",
"1432-2064"
],
"name": "Probability Theory and Related Fields",
"type": "Periodical"
},
{
"issueNumber": "3-4",
"type": "PublicationIssue"
},
{
"type": "PublicationVolume",
"volumeNumber": "173"
}
],
"name": "Fundamental limits of symmetric low-rank matrix estimation",
"pagination": "1-71",
"productId": [
{
"name": "doi",
"type": "PropertyValue",
"value": [
"10.1007/s00440-018-0845-x"
]
},
{
"name": "readcube_id",
"type": "PropertyValue",
"value": [
"7a9e151f5426eadead276b1902d9e873824ddbe84fd312dd73de3b13bbed837d"
]
},
{
"name": "dimensions_id",
"type": "PropertyValue",
"value": [
"pub.1103204637"
]
}
],
"sameAs": [
"https://doi.org/10.1007/s00440-018-0845-x",
"https://app.dimensions.ai/details/publication/pub.1103204637"
],
"sdDataset": "articles",
"sdDatePublished": "2019-04-15T08:58",
"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/v90/0000000375_0000000375/records_91428_00000001.jsonl",
"type": "ScholarlyArticle",
"url": "https://link.springer.com/10.1007%2Fs00440-018-0845-x"
}
]Download the RDF metadata as: json-ld nt turtle xml License info
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/s00440-018-0845-x'
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/s00440-018-0845-x'
Turtle is a human-readable linked data format.
curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/s00440-018-0845-x'
RDF/XML is a standard XML format for linked data.
curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/s00440-018-0845-x'
This table displays all metadata directly associated to this object as RDF triples.
184 TRIPLES
21 PREDICATES
63 URIs
19 LITERALS
7 BLANK NODES