Gaussian Graphical Model Selection Using Graph Compression

Conditional independence between variables in Gaussian graphical models (also known as Gaussian Markov random fields) is represented by the conditional independence graph, \( G \) . Most approaches for inferring conditional independence graph rely on the penalized log-likelihood, where a regularizat...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:ACM transactions on probabilistic machine learning Ročník 1; číslo 2; s. 1 - 25
Hlavní autori: Abolfazli, Mojtaba, Høst-Madsen, Anders, Zhang, June, Bratincsak, Andras
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York, NY ACM 30.06.2025
Predmet:
ISSN:2836-8924, 2836-8924
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Conditional independence between variables in Gaussian graphical models (also known as Gaussian Markov random fields) is represented by the conditional independence graph, \( G \) . Most approaches for inferring conditional independence graph rely on the penalized log-likelihood, where a regularization hyperparameter, \(\lambda\) , controls the preference for either a sparsely or densely connected solution. In this article, we present a method for selecting \(\lambda\) based on the minimum description length (MDL) principle. Our approach improves upon previous methods by better accounting for \( G \) using our novel graph coders. Experiments on known Gaussian graphical models demonstrate that our approach has a higher F1 score in recovering the true conditional independence graph than existing methods, especially when the number of observations is small compared to the number of variables. We also applied our method to a real-world electrocardiogram (ECG) dataset to investigate the inferred conditional independence graph in healthy subjects versus a group of subjects with Kawasaki disease. Finally, we used the learned conditional independence graphs for the classification of healthy subjects versus those with Kawasaki disease.
AbstractList Conditional independence between variables in Gaussian graphical models (also known as Gaussian Markov random fields) is represented by the conditional independence graph, \( G \) . Most approaches for inferring conditional independence graph rely on the penalized log-likelihood, where a regularization hyperparameter, \(\lambda\) , controls the preference for either a sparsely or densely connected solution. In this article, we present a method for selecting \(\lambda\) based on the minimum description length (MDL) principle. Our approach improves upon previous methods by better accounting for \( G \) using our novel graph coders. Experiments on known Gaussian graphical models demonstrate that our approach has a higher F1 score in recovering the true conditional independence graph than existing methods, especially when the number of observations is small compared to the number of variables. We also applied our method to a real-world electrocardiogram (ECG) dataset to investigate the inferred conditional independence graph in healthy subjects versus a group of subjects with Kawasaki disease. Finally, we used the learned conditional independence graphs for the classification of healthy subjects versus those with Kawasaki disease.
ArticleNumber 10
Author Høst-Madsen, Anders
Zhang, June
Bratincsak, Andras
Abolfazli, Mojtaba
Author_xml – sequence: 1
  givenname: Mojtaba
  orcidid: 0000-0001-9437-5126
  surname: Abolfazli
  fullname: Abolfazli, Mojtaba
  email: mojtaba@hawaii.edu
  organization: Department of Electrical and Computer Engineering, University of Hawaii at Manoa, Honolulu, Hawaii, USA
– sequence: 2
  givenname: Anders
  orcidid: 0000-0002-1472-4953
  surname: Høst-Madsen
  fullname: Høst-Madsen, Anders
  email: ahm@hawaii.edu
  organization: Department of Electrical and Computer Engineering, University of Hawaii at Manoa, Honolulu, Hawaii, USA
– sequence: 3
  givenname: June
  orcidid: 0000-0002-4578-5759
  surname: Zhang
  fullname: Zhang, June
  email: zjz@hawaii.edu
  organization: Department of Electrical and Computer Engineering, University of Hawaii at Manoa, Honolulu, Hawaii, USA
– sequence: 4
  givenname: Andras
  orcidid: 0000-0001-8537-827X
  surname: Bratincsak
  fullname: Bratincsak, Andras
  email: andrasb@hphmg.org
  organization: John A. Burns School of Medicine, University of Hawaii at Manoa, Honolulu, Hawaii, USA
BookMark eNpNjz1LxEAYhBc5wfM87K3SWUX3I9kPOwleFE4sPOvwZvddjSTZsKuF_96TnGI1A_PMwJySxRhGJOSc0SvGivJaKCEYNUdkybWQuTa8WPzzJ2Sd0jullBspOFVLclPDZ0odjFkdYXrrLPTZY3DYZ8_Yo_3owpi9pG58nfOsCsMUcd8I4xk59tAnXB90RXabu111n2-f6ofqdptDyUzuFGihOCJS2aIvEFC2vhUtOt5aaaRhJUXDpRWmkCAAtHbeO6e90so5sSKX86yNIaWIvpliN0D8ahhtfk43h9N78mImwQ5_0G_4DXT9U3I
Cites_doi 10.3390/e21030219
10.1109/18.382012
10.1109/TSP.2017.2715000
10.1109/TIT.1981.1056331
10.1109/DCC.1998.672217
10.1109/TSP.2011.2172430
10.1109/ISIT45174.2021.9518002
10.1109/TSP.2019.2935898
10.1109/ISIT.2017.8006795
10.1093/biostatistics/kxm045
10.5555/1953048.2078201
10.1145/1753326.1753532
10.1109/ISIT44484.2020.9174300
10.1093/oso/9780198522195.001.0001
10.1109/TSP.2020.3038480
10.1111/j.1467-9868.2010.00740.x
10.5555/1390681.1390696
10.1609/aaai.v29i1.9277
10.7551/mitpress/4643.001.0001
10.1002/rsa.20842
10.1109/TNNLS.2017.2664100
10.5555/2627435.2697058
10.1093/biomet/81.3.457
10.1214/12-EJS740
10.1093/biomet/asm018
10.1007/s12532-010-0020-6
10.1017/9781108565462
10.1109/ISIT.2019.8849739
10.1371/journal.pone.0014147
10.1016/0005-1098(78)90005-5
10.1109/ISIT.2017.8006796
10.1017/CBO9780511814068
10.1109/18.930936
10.1007/s10994-018-5732-2
10.1016/j.procs.2016.04.102
10.1109/TIT.2011.2173710
10.1109/TSP.2009.2036042
10.1002/j.1538-7305.1948.tb01338.x
10.2307/2528966
10.1145/1217299.1217301
10.1103/RevModPhys.74.47
10.1038/srep05918
10.1162/089976604773717621
10.1109/ISIT.2018.8437551
ContentType Journal Article
Copyright Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from
Copyright_xml – notice: Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from
DBID AAYXX
CITATION
DOI 10.1145/3733109
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef

DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2836-8924
EndPage 25
ExternalDocumentID 10_1145_3733109
3733109
GrantInformation_xml – fundername: NIH
  grantid: 1202518S0
– fundername: NSF
  grantid: CCF-1908957
GroupedDBID AAKMM
ACM
ALMA_UNASSIGNED_HOLDINGS
LHSKQ
M~E
AAYXX
CITATION
ID FETCH-LOGICAL-a519-d7a8372eee06bef4eae6bfb3bed2bc6969150e926c3946a3aa88dffdd8f787dd3
ISSN 2836-8924
IngestDate Sat Nov 29 07:49:31 EST 2025
Mon Jun 30 17:00:02 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Structure Learning
Minimum Description Length
Gaussian Graphical Model Selection
Graph Compression
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-a519-d7a8372eee06bef4eae6bfb3bed2bc6969150e926c3946a3aa88dffdd8f787dd3
ORCID 0000-0002-1472-4953
0000-0002-4578-5759
0000-0001-9437-5126
0000-0001-8537-827X
OpenAccessLink https://dl.acm.org/doi/10.1145/3733109
PageCount 25
ParticipantIDs crossref_primary_10_1145_3733109
acm_primary_3733109
PublicationCentury 2000
PublicationDate 2025-06-30
PublicationDateYYYYMMDD 2025-06-30
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-06-30
  day: 30
PublicationDecade 2020
PublicationPlace New York, NY
PublicationPlace_xml – name: New York, NY
PublicationTitle ACM transactions on probabilistic machine learning
PublicationTitleAbbrev ACM TOPML
PublicationYear 2025
Publisher ACM
Publisher_xml – name: ACM
References (Bib0063) 2009; 37
(Bib0016) 2023
(Bib0060) 1998; 86
(Bib0008) 2001
(Bib0064) 2012; 60
(Bib0054) 2019; 21
(Bib0052) 2015
(Bib0005) 2016
(Bib0024) 2014; 15
(Bib0027) 1981; 27
(Bib0042) 2020; 69
(Bib0046) 2021; 34
(Bib0065) 1995; 41
(Bib0061) 1998
(Bib0051) 2008; 27
(Bib0041) 2012; 6
(Bib0009) 1994; 81
(Bib0022) 2009
(Bib0036) 2010
(Bib0058) 2019; 67
(Bib0044) 2010; 72
(Bib0033) 2007; 1
(Bib0062) 1993; 3
(Bib0056) 1987; 23
(Bib0034) 2010; 2
(Bib0025) 2013; 26
(Bib0057) 2014; 15
(Bib0045) 2010; 5
(Bib0004) 2008; 9
(Bib0015) 1972; 28
(Bib0039) 2019
(Bib0026) 1949
(Bib0050) 1986; 14
(Bib0068) 2017; 29
(Bib0037) 2017; 51
(Bib0066) 2016; 83
(Bib0007) 2018
(Bib0001) 2021
(Bib0059) 2014; 4
(Bib0047) 2017
(Bib0048) 2018; 107
(Bib0069) 2011; 12
(Bib0010) 2009; 58
(Bib0014) 2020
(Bib0049) 1978; 14
(Bib0030) 1996; 17
(Bib0028) 2011; 5
(Bib0013) 2005
(Bib0018) 2017; 65
(Bib0019) 2008; 9
(Bib0035) 2018; 8
(Bib0067) 2007; 94
(Bib0017) 2010
(Bib0020) 2007
(Bib0021) 2001; 47
(Bib0040) 2009
(Bib0003) 2017
(Bib0055) 1948; 27
(Bib0002) 2002; 74
(Bib0023) 2018
(Bib0006) 2015; 9
(Bib0038) 2019; 55
(Bib0031) 2010
(Bib0011) 2012; 58
(Bib0029) 2004; 16
(Bib0043) 2017; 135
(Bib0012) 2006
(Bib0032) 2005
(Bib0053) 2008; 2
Drmota Michael (e_1_3_1_17_2) 2023
Miyaguchi Kohei (e_1_3_1_49_2) 2018; 107
Tan K. M. (e_1_3_1_58_2) 2014; 15
Hastie Trevor (e_1_3_1_23_2) 2009
Menéndez Patricia (e_1_3_1_46_2) 2010; 5
Choi Yongwook (e_1_3_1_12_2) 2012; 58
Li Shibao (e_1_3_1_36_2) 2018; 8
Grünwald Peter D. (e_1_3_1_21_2) 2007
e_1_3_1_66_2
e_1_3_1_22_2
Leon Gordon Kraft (e_1_3_1_27_2) 1949
Van Borkulo Claudia D. (e_1_3_1_60_2) 2014; 4
e_1_3_1_45_2
e_1_3_1_68_2
e_1_3_1_24_2
Shannon Claude E. (e_1_3_1_56_2) 1948; 27
Barber Rina Foygel (e_1_3_1_7_2) 2015; 9
e_1_3_1_8_2
Delgosha Payam (e_1_3_1_15_2) 2020
Liu Han (e_1_3_1_37_2) 2010
e_1_3_1_62_2
Dahl Joachim (e_1_3_1_14_2) 2005
e_1_3_1_20_2
Mazza-Anthony Cody (e_1_3_1_43_2) 2020; 69
Cover T. M. (e_1_3_1_13_2) 2006
Chen Xiang-Hui (e_1_3_1_10_2) 1994; 81
Abolfazli Mojtaba (e_1_3_1_2_2) 2021
Hsieh Cho-Jui (e_1_3_1_26_2) 2013; 26
e_1_3_1_28_2
Albert Réka (e_1_3_1_3_2) 2002; 74
Zhao Xiaozhao (e_1_3_1_69_2) 2017; 29
Miyaguchi Kohei (e_1_3_1_48_2) 2017
Krumsiek Jan (e_1_3_1_29_2) 2011; 5
e_1_3_1_70_2
Wang Yuan H. (e_1_3_1_63_2) 1993; 3
e_1_3_1_55_2
Luczak Tomasz (e_1_3_1_38_2) 2017; 51
e_1_3_1_34_2
e_1_3_1_53_2
Barabási Albert-László (e_1_3_1_6_2) 2016
e_1_3_1_59_2
Meng Xiangming (e_1_3_1_47_2) 2021; 34
e_1_3_1_19_2
Jacobus Hendricus Van Lint (e_1_3_1_61_2) 1998
Wasserman Larry (e_1_3_1_64_2) 2009; 37
Leskovec Jure (e_1_3_1_33_2) 2005
Lange Tilman (e_1_3_1_30_2) 2004; 16
Foygel Rina (e_1_3_1_18_2) 2010
Rissanen Jorma (e_1_3_1_50_2) 1978; 14
e_1_3_1_65_2
e_1_3_1_67_2
Rothman Adam J. (e_1_3_1_54_2) 2008; 2
e_1_3_1_42_2
e_1_3_1_5_2
Choi Myung Jin (e_1_3_1_11_2) 2009; 58
e_1_3_1_25_2
Roos Teemu (e_1_3_1_52_2) 2008; 27
Dempster Arthur P. (e_1_3_1_16_2) 1972; 28
Li Lu (e_1_3_1_35_2) 2010; 2
Leskovec Jure (e_1_3_1_32_2) 2010
McCrindle Brian W. (e_1_3_1_44_2) 2017; 135
Asadi Amir R. (e_1_3_1_4_2) 2017
Rissanen Jorma (e_1_3_1_51_2) 1986; 14
Łuczak Tomasz (e_1_3_1_40_2) 2019
Mikhailovich Shtar’kov Yurii (e_1_3_1_57_2) 1987; 23
e_1_3_1_31_2
Béla Bollobás (e_1_3_1_9_2) 2001
Shaun Lysen (e_1_3_1_41_2) 2009
Łuczak Tomasz (e_1_3_1_39_2) 2019; 55
References_xml – start-page: 177
  year: 2005
  end-page: 187
  ident: Bib0032
  article-title: Graphs over time: Densification laws, shrinking diameters and possible explanations
  publication-title: 11th ACM SIGKDD International Conference on Knowledge Discovery in Data Mining
– start-page: 28
  year: 2009
  ident: Bib0040
  article-title: Permuted inclusion criterion: A variable selection technique
  publication-title: Publicly Accessible Penn Dissertations
– volume: 2
  start-page: 291
  issue: 3–4
  year: 2010
  end-page: 315
  ident: Bib0034
  article-title: An inexact interior point method for \(L_{1}-\) regularized sparse covariance selection
  publication-title: Mathematical Programming Computation
– year: 2006
  ident: Bib0012
  publication-title: Information Theory
– volume: 9
  start-page: 432
  issue: 3
  year: 2008
  end-page: 441
  ident: Bib0019
  article-title: Sparse inverse covariance estimation with the graphical lasso
  publication-title: Biostatistics
– year: 2005
  ident: Bib0013
  publication-title: Maximum Likelihood Estimation of Gaussian Graphical Models: Numerical Implementation and Topology Selection
– volume: 27
  start-page: 256
  issue: 31
  year: 2008
  ident: Bib0051
  article-title: On sequentially normalized maximum likelihood models
  publication-title: Compare
– volume: 3
  start-page: 295
  issue: 2
  year: 1993
  end-page: 312
  ident: Bib0062
  article-title: On the number of successes in independent trials
  publication-title: Statistica Sinica
– start-page: 1432
  year: 2010
  end-page: 1440
  ident: Bib0036
  article-title: Stability approach to regularization selection (StARS) for high dimensional graphical models
  publication-title: In Advances in Neural Information Processing Systems
– volume: 34
  start-page: 6290
  year: 2021
  end-page: 6303
  ident: Bib0046
  article-title: Ising model selection using L1-regularized linear regression: A statistical mechanics analysis
  publication-title: Advances in Neural Information Processing Systems
– volume: 74
  start-page: 47
  issue: 1
  year: 2002
  ident: Bib0002
  article-title: Statistical mechanics of complex networks
  publication-title: Reviews of Modern Physics
– volume: 37
  start-page: 2178
  issue: 5A
  year: 2009
  ident: Bib0063
  article-title: High dimensional variable selection
  publication-title: Annals of Statistics
– volume: 83
  start-page: 82
  year: 2016
  end-page: 89
  ident: Bib0066
  article-title: Link prediction based on common-neighbors for dynamic social network
  publication-title: Procedia Computer Science
– start-page: 723
  year: 2017
  end-page: 731
  ident: Bib0047
  article-title: Sparse graphical modeling via stochastic complexity
  publication-title: 2017 SIAM International Conference on Data Mining
– volume: 21
  start-page: 219
  issue: 3
  year: 2019
  ident: Bib0054
  article-title: Data discovery and anomaly detection using atypicality for real-valued data
  publication-title: Entropy
  doi: 10.3390/e21030219
– year: 2007
  ident: Bib0020
  publication-title: The Minimum Description Length Principle
– volume: 55
  start-page: 696
  issue: 3
  year: 2019
  end-page: 718
  ident: Bib0038
  article-title: Asymmetry and structural information in preferential attachment graphs
  publication-title: Random Structures & Algorithms
– year: 2016
  ident: Bib0005
  publication-title: Network Science
– volume: 41
  start-page: 653
  issue: 3
  year: 1995
  end-page: 664
  ident: Bib0065
  article-title: The context-tree weighting method: basic properties
  publication-title: IEEE Transactions on Information Theory
  doi: 10.1109/18.382012
– volume: 26
  year: 2013
  ident: Bib0025
  article-title: BIG & QUIC: Sparse inverse covariance estimation for a million variables
  publication-title: Advances in Neural Information Processing Systems
– volume: 15
  start-page: 2911
  issue: 1
  year: 2014
  end-page: 2947
  ident: Bib0024
  article-title: QUIC: Quadratic approximation for sparse inverse covariance estimation
  publication-title: The Journal of Machine Learning Research
– start-page: 1361
  year: 2010
  end-page: 1370
  ident: Bib0031
  article-title: Signed networks in social media
  publication-title: SIGCHI Conference on Human Factors in Computing Systems
– volume: 2
  start-page: 494
  year: 2008
  end-page: 515
  ident: Bib0053
  article-title: Sparse permutation invariant covariance estimation
  publication-title: Electronic Journal of Statistics
– volume: 65
  start-page: 5215
  issue: 19
  year: 2017
  end-page: 5224
  ident: Bib0018
  article-title: Bayesian selection for the \(\ell_{2}\) -potts model regularization parameter: 1-D piecewise constant signal denoising
  publication-title: IEEE Transactions on Signal Processing
  doi: 10.1109/TSP.2017.2715000
– volume: 81
  start-page: 457
  issue: 3
  year: 1994
  end-page: 469
  ident: Bib0009
  article-title: Weighted finite population sampling to maximize entropy
  publication-title: Biometrika
– volume: 15
  start-page: 3297
  issue: 2014
  year: 2014
  end-page: 3331
  ident: Bib0057
  article-title: Learning graphical models with hubs
  publication-title: Journal of Machine Learning Research
– volume: 27
  start-page: 199
  issue: 2
  year: 1981
  end-page: 207
  ident: Bib0027
  article-title: The performance of universal encoding
  publication-title: IEEE Transactions on Information Theory
  doi: 10.1109/TIT.1981.1056331
– volume: 8
  start-page: 1
  issue: 1
  year: 2018
  end-page: 11
  ident: Bib0035
  article-title: Similarity-based future common neighbors model for link prediction in complex networks
  publication-title: Scientific Reports
– volume: 5
  start-page: 1
  issue: 1
  year: 2011
  end-page: 16
  ident: Bib0028
  article-title: Gaussian graphical modeling reconstructs pathway reactions from high-throughput metabolomics data
  publication-title: BMC Systems Biology
– volume: 12
  start-page: 2975
  year: 2011
  end-page: 3026
  ident: Bib0069
  article-title: High-dimensional covariance estimation based on Gaussian graphical models
  publication-title: The Journal of Machine Learning Research
– volume: 5
  start-page: e14147
  issue: 12
  year: 2010
  ident: Bib0045
  article-title: Gene regulatory networks from multifactorial perturbations using graphical lasso: Application to the DREAM4 Challenge
  publication-title: PLOS One
– volume: 94
  start-page: 19
  issue: 1
  year: 2007
  end-page: 35
  ident: Bib0067
  article-title: Model selection and estimation in the Gaussian graphical model
  publication-title: Biometrika
– volume: 9
  start-page: 485
  year: 2008
  end-page: 516
  ident: Bib0004
  article-title: Model selection through sparse maximum likelihood estimation for multivariate Gaussian or binary data
  publication-title: Journal of Machine Learning Research
– volume: 9
  start-page: 567
  issue: 1
  year: 2015
  end-page: 607
  ident: Bib0006
  article-title: High-dimensional Ising model selection with Bayesian information criteria
  publication-title: Electronic Journal of Statistics
– volume: 58
  start-page: 620
  issue: 2
  year: 2012
  end-page: 638
  ident: Bib0011
  article-title: Compression of graphical structures: Fundamental limits, algorithms, and experiments
  publication-title: IEEE Transactions on Information Theory
– start-page: 491
  year: 1998
  end-page: 500
  ident: Bib0061
  article-title: Switching between two universal source coding algorithms
  publication-title: DCC ’98 Data Compression Conference
  doi: 10.1109/DCC.1998.672217
– volume: 69
  start-page: 489
  year: 2020
  end-page: 499
  ident: Bib0042
  article-title: Learning Gaussian graphical models with ordered weighted \(L_{1}\) regularization
  publication-title: IEEE Transactions on Signal Processing
– volume: 14
  start-page: 1080
  issue: 3
  year: 1986
  end-page: 1100
  ident: Bib0050
  article-title: Stochastic complexity and modeling
  publication-title: The Annals of Statistics
– year: 2018
  ident: Bib0007
  article-title: Survey and taxonomy of lossless graph compression and space-efficient graph representations
– volume: 135
  start-page: e927
  issue: 17
  year: 2017
  end-page: e999
  ident: Bib0043
  article-title: Diagnosis, treatment, and long-term management of Kawasaki disease: A scientific statement for health professionals from the American Heart Association
  publication-title: Circulation
– volume: 23
  start-page: 3
  issue: 3
  year: 1987
  end-page: 17
  ident: Bib0056
  article-title: Universal sequential coding of single messages
  publication-title: Problemy Peredachi Informatsii
– year: 2009
  ident: Bib0022
  publication-title: The Elements of Statistical Learning Data Mining, Inference, and Prediction
– volume: 107
  start-page: 1283
  year: 2018
  end-page: 1302
  ident: Bib0048
  article-title: High-dimensional penalty selection via minimum description length principle
  publication-title: Machine Learning
– start-page: 1829
  year: 2018
  end-page: 1833
  ident: Bib0023
  article-title: Coding of graphs with application to graph anomaly detection
  publication-title: 2018 IEEE International Symposium on Information Theory (ISIT)
– volume: 60
  start-page: 211
  issue: 1
  year: 2012
  end-page: 220
  ident: Bib0064
  article-title: Distributed covariance estimation in Gaussian graphical models
  publication-title: IEEE Transactions on Signal Processing
  doi: 10.1109/TSP.2011.2172430
– volume: 28
  start-page: 157
  year: 1972
  end-page: 175
  ident: Bib0015
  article-title: Covariance selection
  publication-title: Biometrics
– year: 1949
  ident: Bib0026
  publication-title: A Device for Quantizing, Grouping, and Coding Amplitude-Modulated Pulses
– volume: 29
  start-page: 1608
  issue: 5
  year: 2017
  end-page: 1621
  ident: Bib0068
  article-title: A confident information first principle for parameter reduction and model selection of boltzmann machines
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– start-page: 2708
  year: 2021
  end-page: 2713
  ident: Bib0001
  article-title: Graph coding for model selection and anomaly detection in gaussian graphical models
  publication-title: 2021 IEEE International Symposium on Information Theory (ISIT)
  doi: 10.1109/ISIT45174.2021.9518002
– volume: 58
  start-page: 1012
  issue: 3
  year: 2009
  end-page: 1024
  ident: Bib0010
  article-title: Gaussian multiresolution models: Exploiting sparse Markov and covariance structure
  publication-title: IEEE Transactions on Signal Processing
– volume: 47
  start-page: 2039
  issue: 5
  year: 2001
  end-page: 2041
  ident: Bib0021
  article-title: Binomial and poisson distributions as maximum entropy distributions
  publication-title: IEEE Transactions on Information Theory
– volume: 17
  year: 1996
  ident: Bib0030
  publication-title: Graphical Models
– volume: 4
  start-page: 5918
  year: 2014
  ident: Bib0059
  article-title: A new method for constructing networks from binary data
  publication-title: Scientific Reports
– volume: 51
  start-page: 618015
  year: 2017
  ident: Bib0037
  article-title: Structural information and compression of scale-free graphs
  publication-title: Urbana
– volume: 27
  start-page: 379
  issue: 3
  year: 1948
  end-page: 423
  ident: Bib0055
  article-title: A mathematical theory of communication
  publication-title: The Bell System Technical Journal
– start-page: 2349
  year: 2020
  end-page: 2354
  ident: Bib0014
  article-title: A universal low complexity compression algorithm for sparse marked graphs
  publication-title: 2020 IEEE International Symposium on Information Theory (ISIT)
– year: 2015
  ident: Bib0052
  article-title: The network data repository with interactive graph analytics and visualization
  publication-title: AAAI Conference on Artificial Intelligence
– year: 2023
  ident: Bib0016
  publication-title: Analytic Information Theory: From Compression to Learning
– start-page: 604
  year: 2010
  end-page: 612
  ident: Bib0017
  article-title: Extended Bayesian information criteria for Gaussian graphical models
  publication-title: Advances in Neural Information Processing Systems
– volume: 72
  start-page: 417
  issue: 4
  year: 2010
  end-page: 473
  ident: Bib0044
  article-title: Stability selection
  publication-title: Journal of the Royal Statistical Society: Series B (Statistical Methodology)
– volume: 6
  start-page: 2125
  year: 2012
  ident: Bib0041
  article-title: The graphical lasso: New insights and alternatives
  publication-title: Electronic Journal of Statistics
– year: 2001
  ident: Bib0008
  publication-title: Random Graphs
– start-page: 1697
  year: 2019
  end-page: 1701
  ident: Bib0039
  article-title: Compression of preferential attachment graphs
  publication-title: 2019 IEEE International Symposium on Information Theory (ISIT)
– volume: 16
  start-page: 1299
  issue: 6
  year: 2004
  end-page: 1323
  ident: Bib0029
  article-title: Stability-based validation of clustering solutions
  publication-title: Neural Computation
– volume: 67
  start-page: 5062
  issue: 19
  year: 2019
  end-page: 5077
  ident: Bib0058
  article-title: Edge exclusion tests for graphical model selection: Complex Gaussian vectors and time series
  publication-title: IEEE Transactions on Signal Processing
  doi: 10.1109/TSP.2019.2935898
– start-page: 1583
  year: 2017
  end-page: 1587
  ident: Bib0003
  article-title: Compressing data on graphs with clusters
  publication-title: 2017 IEEE International Symposium on Information Theory (ISIT)
  doi: 10.1109/ISIT.2017.8006795
– volume: 86
  year: 1998
  ident: Bib0060
  publication-title: Introduction to Coding Theory
– volume: 1
  start-page: 2
  issue: 1
  year: 2007
  end-page: es
  ident: Bib0033
  article-title: Graph evolution: Densification and shrinking diameters
  publication-title: ACM Transactions on Knowledge Discovery from Data
– volume: 14
  start-page: 465
  year: 1978
  end-page: 471
  ident: Bib0049
  article-title: Modeling by shortest data description
  publication-title: Automatica
– ident: e_1_3_1_20_2
  doi: 10.1093/biostatistics/kxm045
– volume-title: A Device for Quantizing, Grouping, and Coding Amplitude-Modulated Pulses
  year: 1949
  ident: e_1_3_1_27_2
– ident: e_1_3_1_19_2
  doi: 10.1109/TSP.2017.2715000
– ident: e_1_3_1_70_2
  doi: 10.5555/1953048.2078201
– start-page: 1361
  volume-title: SIGCHI Conference on Human Factors in Computing Systems
  year: 2010
  ident: e_1_3_1_32_2
  doi: 10.1145/1753326.1753532
– start-page: 2349
  volume-title: 2020 IEEE International Symposium on Information Theory (ISIT)
  year: 2020
  ident: e_1_3_1_15_2
  doi: 10.1109/ISIT44484.2020.9174300
– ident: e_1_3_1_31_2
  doi: 10.1093/oso/9780198522195.001.0001
– start-page: 177
  volume-title: 11th ACM SIGKDD International Conference on Knowledge Discovery in Data Mining
  year: 2005
  ident: e_1_3_1_33_2
– volume: 135
  start-page: e927
  issue: 17
  year: 2017
  ident: e_1_3_1_44_2
  article-title: Diagnosis, treatment, and long-term management of Kawasaki disease: A scientific statement for health professionals from the American Heart Association
  publication-title: Circulation
– volume-title: Information Theory
  year: 2006
  ident: e_1_3_1_13_2
– start-page: 28
  year: 2009
  ident: e_1_3_1_41_2
  article-title: Permuted inclusion criterion: A variable selection technique
  publication-title: Publicly Accessible Penn Dissertations
– volume: 69
  start-page: 489
  year: 2020
  ident: e_1_3_1_43_2
  article-title: Learning Gaussian graphical models with ordered weighted \(L_{1}\) regularization
  publication-title: IEEE Transactions on Signal Processing
  doi: 10.1109/TSP.2020.3038480
– ident: e_1_3_1_45_2
  doi: 10.1111/j.1467-9868.2010.00740.x
– ident: e_1_3_1_28_2
  doi: 10.1109/TIT.1981.1056331
– ident: e_1_3_1_5_2
  doi: 10.5555/1390681.1390696
– ident: e_1_3_1_53_2
  doi: 10.1609/aaai.v29i1.9277
– volume-title: The Minimum Description Length Principle
  year: 2007
  ident: e_1_3_1_21_2
  doi: 10.7551/mitpress/4643.001.0001
– volume: 55
  start-page: 696
  issue: 3
  year: 2019
  ident: e_1_3_1_39_2
  article-title: Asymmetry and structural information in preferential attachment graphs
  publication-title: Random Structures & Algorithms
  doi: 10.1002/rsa.20842
– volume-title: Maximum Likelihood Estimation of Gaussian Graphical Models: Numerical Implementation and Topology Selection
  year: 2005
  ident: e_1_3_1_14_2
– start-page: 1432
  year: 2010
  ident: e_1_3_1_37_2
  article-title: Stability approach to regularization selection (StARS) for high dimensional graphical models
  publication-title: In Advances in Neural Information Processing Systems
– volume: 29
  start-page: 1608
  issue: 5
  year: 2017
  ident: e_1_3_1_69_2
  article-title: A confident information first principle for parameter reduction and model selection of boltzmann machines
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
  doi: 10.1109/TNNLS.2017.2664100
– ident: e_1_3_1_25_2
  doi: 10.5555/2627435.2697058
– volume: 5
  start-page: 1
  issue: 1
  year: 2011
  ident: e_1_3_1_29_2
  article-title: Gaussian graphical modeling reconstructs pathway reactions from high-throughput metabolomics data
  publication-title: BMC Systems Biology
– volume: 27
  start-page: 256
  issue: 31
  year: 2008
  ident: e_1_3_1_52_2
  article-title: On sequentially normalized maximum likelihood models
  publication-title: Compare
– ident: e_1_3_1_62_2
  doi: 10.1109/DCC.1998.672217
– volume: 15
  start-page: 3297
  issue: 2014
  year: 2014
  ident: e_1_3_1_58_2
  article-title: Learning graphical models with hubs
  publication-title: Journal of Machine Learning Research
– volume: 81
  start-page: 457
  issue: 3
  year: 1994
  ident: e_1_3_1_10_2
  article-title: Weighted finite population sampling to maximize entropy
  publication-title: Biometrika
  doi: 10.1093/biomet/81.3.457
– volume: 2
  start-page: 494
  year: 2008
  ident: e_1_3_1_54_2
  article-title: Sparse permutation invariant covariance estimation
  publication-title: Electronic Journal of Statistics
– volume: 8
  start-page: 1
  issue: 1
  year: 2018
  ident: e_1_3_1_36_2
  article-title: Similarity-based future common neighbors model for link prediction in complex networks
  publication-title: Scientific Reports
– ident: e_1_3_1_42_2
  doi: 10.1214/12-EJS740
– volume: 34
  start-page: 6290
  year: 2021
  ident: e_1_3_1_47_2
  article-title: Ising model selection using L1-regularized linear regression: A statistical mechanics analysis
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_3_1_66_2
  doi: 10.1109/18.382012
– ident: e_1_3_1_68_2
  doi: 10.1093/biomet/asm018
– volume: 2
  start-page: 291
  issue: 3
  year: 2010
  ident: e_1_3_1_35_2
  article-title: An inexact interior point method for \(L_{1}-\) regularized sparse covariance selection
  publication-title: Mathematical Programming Computation
  doi: 10.1007/s12532-010-0020-6
– ident: e_1_3_1_55_2
  doi: 10.3390/e21030219
– volume: 23
  start-page: 3
  issue: 3
  year: 1987
  ident: e_1_3_1_57_2
  article-title: Universal sequential coding of single messages
  publication-title: Problemy Peredachi Informatsii
– volume-title: Analytic Information Theory: From Compression to Learning
  year: 2023
  ident: e_1_3_1_17_2
  doi: 10.1017/9781108565462
– volume-title: Network Science
  year: 2016
  ident: e_1_3_1_6_2
– volume: 3
  start-page: 295
  issue: 2
  year: 1993
  ident: e_1_3_1_63_2
  article-title: On the number of successes in independent trials
  publication-title: Statistica Sinica
– start-page: 1697
  volume-title: 2019 IEEE International Symposium on Information Theory (ISIT)
  year: 2019
  ident: e_1_3_1_40_2
  doi: 10.1109/ISIT.2019.8849739
– volume: 5
  start-page: e14147
  issue: 12
  year: 2010
  ident: e_1_3_1_46_2
  article-title: Gene regulatory networks from multifactorial perturbations using graphical lasso: Application to the DREAM4 Challenge
  publication-title: PLOS One
  doi: 10.1371/journal.pone.0014147
– volume: 14
  start-page: 465
  year: 1978
  ident: e_1_3_1_50_2
  article-title: Modeling by shortest data description
  publication-title: Automatica
  doi: 10.1016/0005-1098(78)90005-5
– start-page: 1583
  volume-title: 2017 IEEE International Symposium on Information Theory (ISIT)
  year: 2017
  ident: e_1_3_1_4_2
  doi: 10.1109/ISIT.2017.8006796
– volume-title: Random Graphs
  year: 2001
  ident: e_1_3_1_9_2
  doi: 10.1017/CBO9780511814068
– ident: e_1_3_1_22_2
  doi: 10.1109/18.930936
– volume-title: Introduction to Coding Theory
  year: 1998
  ident: e_1_3_1_61_2
– start-page: 2708
  volume-title: 2021 IEEE International Symposium on Information Theory (ISIT)
  year: 2021
  ident: e_1_3_1_2_2
  doi: 10.1109/ISIT45174.2021.9518002
– volume-title: The Elements of Statistical Learning Data Mining, Inference, and Prediction
  year: 2009
  ident: e_1_3_1_23_2
– volume: 107
  start-page: 1283
  year: 2018
  ident: e_1_3_1_49_2
  article-title: High-dimensional penalty selection via minimum description length principle
  publication-title: Machine Learning
  doi: 10.1007/s10994-018-5732-2
– volume: 14
  start-page: 1080
  issue: 3
  year: 1986
  ident: e_1_3_1_51_2
  article-title: Stochastic complexity and modeling
  publication-title: The Annals of Statistics
– start-page: 604
  year: 2010
  ident: e_1_3_1_18_2
  article-title: Extended Bayesian information criteria for Gaussian graphical models
  publication-title: Advances in Neural Information Processing Systems
– start-page: 723
  volume-title: 2017 SIAM International Conference on Data Mining
  year: 2017
  ident: e_1_3_1_48_2
– ident: e_1_3_1_67_2
  doi: 10.1016/j.procs.2016.04.102
– volume: 58
  start-page: 620
  issue: 2
  year: 2012
  ident: e_1_3_1_12_2
  article-title: Compression of graphical structures: Fundamental limits, algorithms, and experiments
  publication-title: IEEE Transactions on Information Theory
  doi: 10.1109/TIT.2011.2173710
– ident: e_1_3_1_8_2
– volume: 58
  start-page: 1012
  issue: 3
  year: 2009
  ident: e_1_3_1_11_2
  article-title: Gaussian multiresolution models: Exploiting sparse Markov and covariance structure
  publication-title: IEEE Transactions on Signal Processing
  doi: 10.1109/TSP.2009.2036042
– volume: 37
  start-page: 2178
  issue: 5
  year: 2009
  ident: e_1_3_1_64_2
  article-title: High dimensional variable selection
  publication-title: Annals of Statistics
– volume: 27
  start-page: 379
  issue: 3
  year: 1948
  ident: e_1_3_1_56_2
  article-title: A mathematical theory of communication
  publication-title: The Bell System Technical Journal
  doi: 10.1002/j.1538-7305.1948.tb01338.x
– volume: 28
  start-page: 157
  year: 1972
  ident: e_1_3_1_16_2
  article-title: Covariance selection
  publication-title: Biometrics
  doi: 10.2307/2528966
– ident: e_1_3_1_34_2
  doi: 10.1145/1217299.1217301
– volume: 74
  start-page: 47
  issue: 1
  year: 2002
  ident: e_1_3_1_3_2
  article-title: Statistical mechanics of complex networks
  publication-title: Reviews of Modern Physics
  doi: 10.1103/RevModPhys.74.47
– volume: 4
  start-page: 5918
  year: 2014
  ident: e_1_3_1_60_2
  article-title: A new method for constructing networks from binary data
  publication-title: Scientific Reports
  doi: 10.1038/srep05918
– volume: 26
  year: 2013
  ident: e_1_3_1_26_2
  article-title: BIG & QUIC: Sparse inverse covariance estimation for a million variables
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_3_1_65_2
  doi: 10.1109/TSP.2011.2172430
– volume: 51
  start-page: 618015
  year: 2017
  ident: e_1_3_1_38_2
  article-title: Structural information and compression of scale-free graphs
  publication-title: Urbana
– ident: e_1_3_1_59_2
  doi: 10.1109/TSP.2019.2935898
– volume: 16
  start-page: 1299
  issue: 6
  year: 2004
  ident: e_1_3_1_30_2
  article-title: Stability-based validation of clustering solutions
  publication-title: Neural Computation
  doi: 10.1162/089976604773717621
– volume: 9
  start-page: 567
  issue: 1
  year: 2015
  ident: e_1_3_1_7_2
  article-title: High-dimensional Ising model selection with Bayesian information criteria
  publication-title: Electronic Journal of Statistics
– ident: e_1_3_1_24_2
  doi: 10.1109/ISIT.2018.8437551
SSID ssj0002963207
Score 2.295888
Snippet Conditional independence between variables in Gaussian graphical models (also known as Gaussian Markov random fields) is represented by the conditional...
SourceID crossref
acm
SourceType Index Database
Publisher
StartPage 1
SubjectTerms Computing methodologies
Graph algorithms
Information theory
Learning in probabilistic graphical models
Mathematics of computing
SubjectTermsDisplay Computing methodologies -- Learning in probabilistic graphical models
Mathematics of computing -- Graph algorithms
Mathematics of computing -- Information theory
Title Gaussian Graphical Model Selection Using Graph Compression
URI https://dl.acm.org/doi/10.1145/3733109
Volume 1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2836-8924
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0002963207
  issn: 2836-8924
  databaseCode: M~E
  dateStart: 20250101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELaWlgOXQguIlod86A0Zdh3HsXtbKmiFuhWHFeqtmsRj1LJNq262qjjwJ_qH8SPOpi0ScOASRXYcRZ7RzMQz33yEbCPaytoMmHfmzEXElkGRC4ZGWC48CUdo9vz1oDg8VEdH-stgcJOwMFezoq7V9bW--K-idmNO2B46-w_i7l7qBty9E7q7OrG7618Jfg8W84CM3PO9qIMMPOHZzJmFGUZi8FgnEOaDQYi1sHU_UB3vTjx9ROISD0kFTz4TGvL63s5vz0IZJibeiW-9RNLMwo8Iu56cnzZQdqZ_3-flP6h5wyZg2rOfcYDX3DvA_ry4lfBvTupqDt9TDSbcOq7geaqtS1bNhTOSKR2B0-_wN2PJLPe0j_dM7KjnqyNm-r4XEL5hRubpKId66ehScv-O_-uqEiNGOz9uFz4gq7zIta8TnPxcHtxxZ7J4gOF3nx3B2H7t-3atj3Wqs16s0wtapk_IWvu3QcdRS9bJAOsN8jgxedDWsD8lO0lpaKc0NCgN7ZSGBqWJ87SnNM_I9NPH6e4-a1k1GLhonZkCVFZwRBzKEq1AQFnaMivR8LKSWmr3i4CayyrTQkIGoJSx1hhlnW03JntOVurzGl8QChn6_o4yF9YKgahGIxhqEIXvmaeHcpNsuE04vohtU9K2bhKaNqWburPzW39-5CV5tNSuV2SluVzga_KwumpO5pdvgsR-AZMvaL0
linkProvider ISSN International Centre
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=Gaussian+Graphical+Model+Selection+Using+Graph+Compression&rft.jtitle=ACM+transactions+on+probabilistic+machine+learning&rft.au=Abolfazli%2C+Mojtaba&rft.au=H%C3%B8st-Madsen%2C+Anders&rft.au=Zhang%2C+June&rft.au=Bratincsak%2C+Andras&rft.date=2025-06-30&rft.issn=2836-8924&rft.eissn=2836-8924&rft.volume=1&rft.issue=2&rft.spage=1&rft.epage=25&rft_id=info:doi/10.1145%2F3733109&rft.externalDBID=n%2Fa&rft.externalDocID=10_1145_3733109
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2836-8924&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2836-8924&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2836-8924&client=summon