Vector Gaussian CEO Problem Under Logarithmic Loss and Applications

In this paper, we study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, <inline-formula> <tex-math notation="LaTeX">{K} \geq 2 </tex-math></inline-formula> agents observe independently corrupted Gaus...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on information theory Ročník 66; číslo 7; s. 4183 - 4202
Hlavní autori: Ugur, Yigit, Aguerri, Inaki Estella, Zaidi, Abdellatif
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 01.07.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Predmet:
ISSN:0018-9448, 1557-9654
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract In this paper, we study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, <inline-formula> <tex-math notation="LaTeX">{K} \geq 2 </tex-math></inline-formula> agents observe independently corrupted Gaussian noisy versions of a remote vector Gaussian source, and communicate independently with a decoder or CEO over rate-constrained noise-free links. The CEO also has its own Gaussian noisy observation of the source and wants to reconstruct the remote source to within some prescribed distortion level where the incurred distortion is measured under the logarithmic loss penalty criterion. We find an explicit characterization of the rate-distortion region of this model. The result can be seen as the counterpart to the vector Gaussian setting of that by Courtade-Weissman which provides the rate-distortion region of the model in the discrete memoryless setting. For the proof of this result, we obtain an outer bound by means of a technique that relies on the de Bruijn identity and the properties of Fisher information. The approach is similar to Ekrem-Ulukus outer bounding technique for the vector Gaussian CEO problem under quadratic distortion measure, for which it was there found generally non-tight; but it is shown here to yield a complete characterization of the region for the case of logarithmic loss measure. Also, we show that Gaussian test channels with time-sharing exhaust the Berger-Tung inner bound, which is optimal. Furthermore, application of our results allows us to find the complete solutions of two related problems: a quadratic vector Gaussian CEO problem with determinant constraint and the vector Gaussian distributed Information Bottleneck problem. Finally, we develop Blahut-Arimoto type algorithms that allow to compute numerically the regions provided in this paper, for both discrete and Gaussian models. With the known relevance of the logarithmic loss fidelity measure in the context of learning and prediction, the proposed algorithms may find usefulness in a variety of applications where learning is performed distributively. We illustrate the efficiency of our algorithms through some numerical examples.
AbstractList In this paper, we study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, <inline-formula> <tex-math notation="LaTeX">{K} \geq 2 </tex-math></inline-formula> agents observe independently corrupted Gaussian noisy versions of a remote vector Gaussian source, and communicate independently with a decoder or CEO over rate-constrained noise-free links. The CEO also has its own Gaussian noisy observation of the source and wants to reconstruct the remote source to within some prescribed distortion level where the incurred distortion is measured under the logarithmic loss penalty criterion. We find an explicit characterization of the rate-distortion region of this model. The result can be seen as the counterpart to the vector Gaussian setting of that by Courtade-Weissman which provides the rate-distortion region of the model in the discrete memoryless setting. For the proof of this result, we obtain an outer bound by means of a technique that relies on the de Bruijn identity and the properties of Fisher information. The approach is similar to Ekrem-Ulukus outer bounding technique for the vector Gaussian CEO problem under quadratic distortion measure, for which it was there found generally non-tight; but it is shown here to yield a complete characterization of the region for the case of logarithmic loss measure. Also, we show that Gaussian test channels with time-sharing exhaust the Berger-Tung inner bound, which is optimal. Furthermore, application of our results allows us to find the complete solutions of two related problems: a quadratic vector Gaussian CEO problem with determinant constraint and the vector Gaussian distributed Information Bottleneck problem. Finally, we develop Blahut-Arimoto type algorithms that allow to compute numerically the regions provided in this paper, for both discrete and Gaussian models. With the known relevance of the logarithmic loss fidelity measure in the context of learning and prediction, the proposed algorithms may find usefulness in a variety of applications where learning is performed distributively. We illustrate the efficiency of our algorithms through some numerical examples.
In this paper, we study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, [Formula Omitted] agents observe independently corrupted Gaussian noisy versions of a remote vector Gaussian source, and communicate independently with a decoder or CEO over rate-constrained noise-free links. The CEO also has its own Gaussian noisy observation of the source and wants to reconstruct the remote source to within some prescribed distortion level where the incurred distortion is measured under the logarithmic loss penalty criterion. We find an explicit characterization of the rate-distortion region of this model. The result can be seen as the counterpart to the vector Gaussian setting of that by Courtade-Weissman which provides the rate-distortion region of the model in the discrete memoryless setting. For the proof of this result, we obtain an outer bound by means of a technique that relies on the de Bruijn identity and the properties of Fisher information. The approach is similar to Ekrem-Ulukus outer bounding technique for the vector Gaussian CEO problem under quadratic distortion measure, for which it was there found generally non-tight; but it is shown here to yield a complete characterization of the region for the case of logarithmic loss measure. Also, we show that Gaussian test channels with time-sharing exhaust the Berger-Tung inner bound, which is optimal. Furthermore, application of our results allows us to find the complete solutions of two related problems: a quadratic vector Gaussian CEO problem with determinant constraint and the vector Gaussian distributed Information Bottleneck problem. Finally, we develop Blahut-Arimoto type algorithms that allow to compute numerically the regions provided in this paper, for both discrete and Gaussian models. With the known relevance of the logarithmic loss fidelity measure in the context of learning and prediction, the proposed algorithms may find usefulness in a variety of applications where learning is performed distributively. We illustrate the efficiency of our algorithms through some numerical examples.
We study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, K≥2 agents observe independently corrupted Gaussian noisy versions of a remote vector Gaussian source, and communicate independently with a decoder or CEO over rate-constrained noise-free links. The CEO also has its own Gaussian noisy observation of the source and wants to reconstruct the remote source to within some prescribed distortion level where the incurred distortion is measured under the logarithmic loss penalty criterion. We find an explicit characterization of the rate-distortion region of this model. The result can be seen as the counterpart to the vector Gaussian setting of that by Courtade-Weissman which provides the rate-distortion region of the model in the discrete memoryless setting. For the proof of this result, we obtain an outer bound by means of a technique that relies on the de Bruijn identity and the properties of Fisher information. The approach is similar to Ekrem-Ulukus outer bounding technique for the vector Gaussian CEO problem under quadratic distortion measure, for which it was there found generally non-tight; but it is shown here to yield a complete characterization of the region for the case of logarithmic loss measure. Also, we show that Gaussian test channels with time-sharing exhaust the Berger-Tung inner bound, which is optimal. Furthermore, application of our results allows us to find the complete solutions of two related problems: a quadratic vector Gaussian CEO problem with determinant constraint and the vector Gaussian distributed Information Bottleneck problem. Finally, we develop Blahut-Arimoto type algorithms that allow to compute numerically the regions provided in this paper, for both discrete and Gaussian models. We illustrate the efficiency of our algorithms through some numerical examples.
Author Zaidi, Abdellatif
Ugur, Yigit
Aguerri, Inaki Estella
Author_xml – sequence: 1
  givenname: Yigit
  orcidid: 0000-0003-1835-6964
  surname: Ugur
  fullname: Ugur, Yigit
  email: ygtugur@gmail.com
  organization: Laboratoire d’informatique Gaspard-Monge, Université Paris-Est, Champs-sur-Marne, France
– sequence: 2
  givenname: Inaki Estella
  surname: Aguerri
  fullname: Aguerri, Inaki Estella
  email: inaki.estella@gmail.com
  organization: Mathematical and Algorithmic Sciences Laboratory, Paris Research Center, Huawei Technologies, Boulogne-Billancourt, France
– sequence: 3
  givenname: Abdellatif
  orcidid: 0000-0003-2023-9476
  surname: Zaidi
  fullname: Zaidi, Abdellatif
  email: abdellatif.zaidi@u-pem.fr
  organization: Laboratoire d’informatique Gaspard-Monge, Université Paris-Est, Champs-sur-Marne, France
BackLink https://hal.science/hal-04456090$$DView record in HAL
BookMark eNp9kM9LwzAcxYMouE3vgpeCJw-d-dkmx1HmNijMw-Y1pGnqMrq2Jp3gf29mpwcPXr75JnxeeO-NwWXTNgaAOwSnCEHxtFltphhiOMUixYTyCzBCjKWxSBi9BCMIEY8FpfwajL3fhytlCI9A9mp037pooY7eW9VE2Xwdvbi2qM0h2jalcVHeviln-93B6rB7H6mmjGZdV1utets2_gZcVar25vZ8TsD2eb7JlnG-XqyyWR5rglkfZoITwZAhqsBUG0WJYkRjmLIiLcqUB0eoqoggDKoE8ZIQqiAuWIqRQISQCXgc_t2pWnbOHpT7lK2ycjnL5ekNUsoSKOAHCuzDwHaufT8a38t9e3RNsCcxRUwITBgPVDJQ2oVgzlRS2_47VO-UrSWC8lSuDOXKU7nyXG4Qwj_CHz__SO4HiTXG_OJc8CRllHwBmp-DLg
CODEN IETTAW
CitedBy_id crossref_primary_10_1109_TCOMM_2023_3274122
crossref_primary_10_3390_info12040155
crossref_primary_10_1109_TCOMM_2023_3317916
crossref_primary_10_1109_TWC_2022_3191118
crossref_primary_10_1109_TIT_2020_3019654
crossref_primary_10_1109_TIT_2020_2993172
crossref_primary_10_1109_TIT_2022_3214433
crossref_primary_10_1109_TIT_2025_3532280
crossref_primary_10_1109_TCOMM_2021_3097142
crossref_primary_10_1109_OJCOMS_2025_3570446
crossref_primary_10_3390_e24040438
crossref_primary_10_1109_TCOMM_2022_3163768
crossref_primary_10_1109_TIFS_2024_3522775
crossref_primary_10_1109_JSAC_2022_3223408
crossref_primary_10_3390_e23070862
crossref_primary_10_1109_OJCOMS_2025_3605737
crossref_primary_10_1109_TIT_2021_3073533
crossref_primary_10_3390_e24091321
crossref_primary_10_1109_TIT_2021_3107215
crossref_primary_10_1109_LCOMM_2023_3236167
crossref_primary_10_1109_TIT_2022_3208814
crossref_primary_10_1109_TCOMM_2024_3523975
crossref_primary_10_1109_TIT_2024_3371065
Cites_doi 10.1017/CBO9780511546921
10.1109/TIT.2015.2462848
10.1109/TIT.2008.928951
10.1109/78.995062
10.1109/TIT.2008.920343
10.1109/ISIT.2011.6033916
10.1109/ISIT.2004.1365218
10.1109/TIT.2005.859248
10.1109/ICIP.2006.312762
10.1109/TIT.2017.2700857
10.1109/TIT.2013.2288257
10.1109/TIT.1972.1054855
10.1109/TIT.2008.924659
10.1109/TIT.2016.2617862
10.1109/ISIT.2014.6875354
10.1109/TIT.2008.917687
10.1109/CISS.2014.6814120
10.1109/TIT.2019.2897564
10.1109/ALLERTON.2014.7028531
10.1109/TIT.2005.860424
10.1109/TIT.2012.2206793
10.1109/ISIT.2004.1365154
10.1109/ISIT.2011.6033913
10.1109/ISIT.2012.6283628
10.1109/ISIT.2017.8006893
10.1109/TIT.2016.2570011
10.1109/ISIT.2018.8437786
10.1109/TIT.2007.894680
10.1109/TIT.2017.2779745
10.1109/TIT.2009.2027519
10.1109/ISIT.2017.8006710
10.1109/TIT.1986.1057194
10.1109/ITW.2018.8613480
10.1109/TIT.2014.2358692
10.1109/ISIT.2004.1365217
10.1109/ISIT.2018.8437318
10.1109/TIT.2006.880064
10.1109/TIT.1972.1054753
10.1109/ISIT.2007.4557285
10.1109/ITW.2017.8277967
10.1109/TCOMM.2018.2798659
10.1109/TSP.2003.815393
10.1109/18.104312
10.1137/120891009
10.1109/TIT.2003.822581
10.1109/ACSSC.2005.1599689
10.1109/TIT.2011.2120030
10.1109/TIT.2016.2531080
10.1109/TIT.2005.850110
10.1109/ISIT.2012.6284256
10.1109/TIT.1987.1057383
10.1109/ISIT.2015.7282839
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020
– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
1XC
DOI 10.1109/TIT.2020.2972348
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Hyper Article en Ligne (HAL)
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Technology Research Database

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
Mathematics
EISSN 1557-9654
EndPage 4202
ExternalDocumentID oai:HAL:hal-04456090v1
10_1109_TIT_2020_2972348
8986754
Genre orig-research
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACGFS
ACGOD
ACIWK
AENEX
AETEA
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
E.L
EBS
EJD
F5P
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
MS~
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
RXW
TAE
TN5
VH1
VJK
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
1XC
ID FETCH-LOGICAL-c325t-c3626951e3ab24cea43a53c2075b7bd784511ff39350a618d334a02b572191333
IEDL.DBID RIE
ISICitedReferencesCount 34
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000544995900014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9448
IngestDate Sun Oct 19 06:22:54 EDT 2025
Mon Jun 30 05:36:22 EDT 2025
Tue Nov 18 22:21:56 EST 2025
Sat Nov 29 03:31:43 EST 2025
Wed Aug 27 02:39:13 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 7
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c325t-c3626951e3ab24cea43a53c2075b7bd784511ff39350a618d334a02b572191333
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-1835-6964
0000-0003-2023-9476
PQID 2415992358
PQPubID 36024
PageCount 20
ParticipantIDs crossref_citationtrail_10_1109_TIT_2020_2972348
crossref_primary_10_1109_TIT_2020_2972348
hal_primary_oai_HAL_hal_04456090v1
ieee_primary_8986754
proquest_journals_2415992358
PublicationCentury 2000
PublicationDate 2020-07-01
PublicationDateYYYYMMDD 2020-07-01
PublicationDate_xml – month: 07
  year: 2020
  text: 2020-07-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on information theory
PublicationTitleAbbrev TIT
PublicationYear 2020
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Institute of Electrical and Electronics Engineers
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
– name: Institute of Electrical and Electronics Engineers
References ref13
ref12
ref59
ref15
ref58
ref11
ref10
ref17
ref16
chechik (ref26) 2005; 6
ref19
ref18
courtade (ref61) 2014
russo (ref55) 2015
ref50
ref46
ref45
ref48
ref42
ref41
ref44
ref43
courtade (ref47) 2015
baram (ref52) 2004; 5
ref49
ref8
ref7
ref9
ref4
ref3
ref6
grant (ref60) 2014
ref5
ref40
ref35
ref34
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref1
ref39
ref38
asadi (ref57) 2018
tishby (ref14) 1999
ref24
ref23
aguerri (ref54) 0
ref25
ref64
ref20
xu (ref56) 2017
ref63
aguerri (ref53) 2018
ref22
ref21
ref28
ref27
ref29
slonim (ref51) 2001
ref62
References_xml – ident: ref15
  doi: 10.1017/CBO9780511546921
– start-page: 191
  year: 2001
  ident: ref51
  article-title: The power of word clusters for text classification
  publication-title: Proc 23rd Eur Colloq Inf Retr Res
– ident: ref11
  doi: 10.1109/TIT.2015.2462848
– ident: ref44
  doi: 10.1109/TIT.2008.928951
– ident: ref22
  doi: 10.1109/78.995062
– ident: ref49
  doi: 10.1109/TIT.2008.920343
– ident: ref5
  doi: 10.1109/ISIT.2011.6033916
– ident: ref31
  doi: 10.1109/ISIT.2004.1365218
– ident: ref29
  doi: 10.1109/TIT.2005.859248
– ident: ref16
  doi: 10.1109/ICIP.2006.312762
– ident: ref40
  doi: 10.1109/TIT.2017.2700857
– ident: ref10
  doi: 10.1109/TIT.2013.2288257
– ident: ref24
  doi: 10.1109/TIT.1972.1054855
– ident: ref36
  doi: 10.1109/TIT.2008.924659
– ident: ref46
  doi: 10.1109/TIT.2016.2617862
– year: 2015
  ident: ref47
  article-title: Gaussian multiterminal source coding through the lens of logarithmic loss
  publication-title: Proc Inf Theory Appl Workshop
– ident: ref28
  doi: 10.1109/ISIT.2014.6875354
– ident: ref58
  doi: 10.1109/TIT.2008.917687
– ident: ref27
  doi: 10.1109/CISS.2014.6814120
– ident: ref39
  doi: 10.1109/TIT.2019.2897564
– ident: ref50
  doi: 10.1109/ALLERTON.2014.7028531
– ident: ref64
  doi: 10.1109/TIT.2005.860424
– ident: ref43
  doi: 10.1109/TIT.2012.2206793
– ident: ref4
  doi: 10.1109/ISIT.2004.1365154
– volume: 5
  start-page: 255
  year: 2004
  ident: ref52
  article-title: Online choice of active learning algorithms
  publication-title: J Mach Learn Res
– ident: ref9
  doi: 10.1109/ISIT.2011.6033913
– volume: 6
  start-page: 165
  year: 2005
  ident: ref26
  article-title: Information bottleneck for Gaussian variables
  publication-title: J Mach Learn Res
– ident: ref62
  doi: 10.1109/ISIT.2012.6283628
– ident: ref38
  doi: 10.1109/ISIT.2017.8006893
– year: 2014
  ident: ref60
  publication-title: CVX MATLAB Software for Disciplined Convex Programming
– ident: ref17
  doi: 10.1109/TIT.2016.2570011
– ident: ref33
  doi: 10.1109/ISIT.2018.8437786
– ident: ref7
  doi: 10.1109/TIT.2007.894680
– ident: ref48
  doi: 10.1109/TIT.2017.2779745
– ident: ref35
  doi: 10.1109/TIT.2009.2027519
– ident: ref13
  doi: 10.1109/ISIT.2017.8006710
– ident: ref41
  doi: 10.1109/TIT.1986.1057194
– ident: ref2
  doi: 10.1109/ITW.2018.8613480
– ident: ref18
  doi: 10.1109/TIT.2014.2358692
– ident: ref32
  doi: 10.1109/ISIT.2004.1365217
– start-page: 35
  year: 2018
  ident: ref53
  article-title: Distributed information bottleneck method for discrete and Gaussian sources
  publication-title: Proc IEEE Int Zurich Seminar Inf Commun
– ident: ref34
  doi: 10.1109/ISIT.2018.8437318
– ident: ref20
  doi: 10.1109/TIT.2006.880064
– ident: ref25
  doi: 10.1109/TIT.1972.1054753
– ident: ref23
  doi: 10.1109/ISIT.2007.4557285
– ident: ref1
  doi: 10.1109/ITW.2017.8277967
– ident: ref45
  doi: 10.1109/TCOMM.2018.2798659
– ident: ref21
  doi: 10.1109/TSP.2003.815393
– ident: ref63
  doi: 10.1109/18.104312
– ident: ref59
  doi: 10.1137/120891009
– ident: ref30
  doi: 10.1109/TIT.2003.822581
– ident: ref19
  doi: 10.1109/ACSSC.2005.1599689
– start-page: 2524
  year: 2017
  ident: ref56
  article-title: Information-theoretic analysis of generalization capability of learning algorithms
  publication-title: Proc Proc Conf Neural Inf Process Syst
– ident: ref37
  doi: 10.1109/TIT.2011.2120030
– ident: ref8
  doi: 10.1109/TIT.2016.2531080
– ident: ref3
  doi: 10.1109/TIT.2005.850110
– start-page: 368
  year: 1999
  ident: ref14
  article-title: The information bottleneck method
  publication-title: Proc 37th Annu Allerton Conf Commun Control Comput
– year: 2015
  ident: ref55
  article-title: How much does your data exploration overfit? Controlling bias via information usage
  publication-title: arXiv 1511 05219
– year: 0
  ident: ref54
  article-title: Distributed variational representation learning
  publication-title: IEEE Trans Pattern Anal Mach Intell
– ident: ref6
  doi: 10.1109/ISIT.2012.6284256
– ident: ref42
  doi: 10.1109/TIT.1987.1057383
– start-page: 7234
  year: 2018
  ident: ref57
  article-title: Chaining mutual information and tightening generalization bounds
  publication-title: Proc 32nd Conf Neural Inf Process Syst
– start-page: 33
  year: 2014
  ident: ref61
  article-title: On an extremal data processing inequality for long Markov chains
  publication-title: Proc IEEE Int Zurich Seminar Inf Commun
– ident: ref12
  doi: 10.1109/ISIT.2015.7282839
SSID ssj0014512
Score 2.533248
Snippet In this paper, we study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, <inline-formula>...
In this paper, we study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, [Formula Omitted]...
We study the vector Gaussian Chief Executive Officer (CEO) problem under logarithmic loss distortion measure. Specifically, K≥2 agents observe independently...
SourceID hal
proquest
crossref
ieee
SourceType Open Access Repository
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 4183
SubjectTerms Algorithms
Berger-Tung inner bound
Blahut-Arimoto algorithm
CEO problem
Chief executive officers
Codes
Constraints
Decoding
Distortion
Distortion measurement
distributed source coding
information bottleneck
Information Theory
logarithmic loss
Loss measurement
Machine learning
Mathematical models
Mathematics
Multiterminal source coding
Noise measurement
Rate-distortion
rate-distortion region
Remote observing
Source coding
Title Vector Gaussian CEO Problem Under Logarithmic Loss and Applications
URI https://ieeexplore.ieee.org/document/8986754
https://www.proquest.com/docview/2415992358
https://hal.science/hal-04456090
Volume 66
WOSCitedRecordID wos000544995900014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 1557-9654
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014512
  issn: 0018-9448
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFD644YM-eBenU4L4IliXJr3lcQxvMKYPU3wrSZq6gW6ybv5-T9KuDBTBlxJKUkK-JjlfTs75AC5wC6RUK-0pqkIvYH7uKSaMx_JAGx6Evoy0E5uIB4Pk9VU8rcFVHQtjjHGXz8y1LTpffjbVC3tU1klEgvZt0IBGHMdlrFbtMcDPlpnBfZzAyDmWLkkqOsOHIRJBRq-ZldiySj8rW1BjZC9AOmWVH8ux22Nut__Xux3YqmxJ0i3B34U1M9mD7aVOA6mm7R5sriQd3IfeizuoJ3dyUdgIStK7eSRPpa4McTJIpD99Qwo9H32MNZaLgshJRrorru4DeL69GfbuvUpKwdOchXN8InFBY8pwqRiiIAMuQ64ZGgwqVlmc2DRleW7jdKmM_CTjPJCUqRAJokAayw-hOZlOzBGQyEShr6XiWZQFeRSpKKZZjEuBr1gi_awFneXoprrKM27lLt5TxzeoSBGP1OKRVni04LJu8Vnm2Pij7jkCVlezybHvu_3UvqMBGoNU0C-_BfsWnrpWhUwL2kt802qmFqm1YISwAcPHv7c6gQ3bgfKKbhua89nCnMK6_pqPi9mZ-wm_ASxq1gA
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bT9swFD7iJsEexrhpZbBZaC9IhDq2c_FjVcGK1hUeOsSbZTvOQNraibT8fo6dNKoEQuIlsiLbsvLF9vl8fM4H8B23QEqtsZGhJokEi8vIMOkiVgrruEhindogNpGNRvndnbxZgbM2FsY5Fy6fuXNfDL78Ymrn_qism8sc7VuxCuuJwG7raK3WZ4Ad17nBY5zCyDoWTkkqu-OrMVJBRs-ZF9nyWj9Lm9Dqvb8CGbRVXizIYZe53H7f-D7Bx8aaJL0a_h1YcZNd2F4oNZBm4u7Ch6W0g3vQvw1H9eSHnlc-hpL0L67JTa0sQ4IQEhlO_yCJnt3_e7BYriqiJwXpLTm79-H35cW4P4gaMYXIcpbM8InUBc0px7VhiIMWXCfcMjQZTGaKLPeJysrSR-pSncZ5wbnQlJkEKaJEIssPYG0ynbjPQFKXJrHVhhdpIco0NWlGiwwXg9iwXMdFB7qLr6tsk2ncC178VYFxUKkQD-XxUA0eHThtW_yvs2y8UfcEAWur-fTYg95Q-XdUoDlIJX2KO7Dn4WlrNch04GiBr2rmaqW8DSOlDxk-fL3VN9gcjH8N1fBq9PMLbPnB1Bd2j2Bt9jh3x7Bhn2YP1ePX8EM-A3oG2Uc
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Vector+Gaussian+CEO+Problem+Under+Logarithmic+Loss+and+Applications&rft.jtitle=IEEE+transactions+on+information+theory&rft.au=Ugur%2C+Yigit&rft.au=Aguerri%2C+Inaki+Estella&rft.au=Zaidi%2C+Abdellatif&rft.date=2020-07-01&rft.pub=IEEE&rft.issn=0018-9448&rft.volume=66&rft.issue=7&rft.spage=4183&rft.epage=4202&rft_id=info:doi/10.1109%2FTIT.2020.2972348&rft.externalDocID=8986754
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9448&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9448&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9448&client=summon