-
Notifications
You must be signed in to change notification settings - Fork 0
/
PLoS_SI_Supp.bib
188 lines (174 loc) · 15.3 KB
/
PLoS_SI_Supp.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
@inproceedings{gretton_nonlinear_2009,
title = {Nonlinear directed acyclic structure learning with weakly additive noise models},
pages = {1847--1855},
booktitle = {Advances in neural information processing systems},
author = {Gretton, Arthur and Spirtes, Peter and Tillman, Robert E.},
date = {2009},
keywords = {Additive noise model, {HSIC}, {kPC}},
file = {Fulltext:/home/vcabeli/Zotero/storage/BSKC6E2G/Gretton et al. - 2009 - Nonlinear directed acyclic structure learning with.pdf:application/pdf;Snapshot:/home/vcabeli/Zotero/storage/WA4F59XV/3699-nonlinear-directed-acyclic-structure-learning-with-weakly-additive-noise-models.html:text/html;Snapshot:/home/vcabeli/Zotero/storage/K5MCXDWU/3699-nonlinear-directed-acyclic-structure-learning-with-weakly-additive-noise-models.html:text/html}
}
@article{gretton_kernel_2005,
title = {Kernel methods for measuring independence},
volume = {6},
pages = {2075--2129},
issue = {Dec},
journaltitle = {Journal of Machine Learning Research},
author = {Gretton, Arthur and Herbrich, Ralf and Smola, Alexander and Bousquet, Olivier and Schölkopf, Bernhard},
date = {2005},
file = {Fulltext:/home/vcabeli/Zotero/storage/95PHYPR7/Gretton et al. - 2005 - Kernel methods for measuring independence.pdf:application/pdf;Snapshot:/home/vcabeli/Zotero/storage/74Q5L3I6/gretton05a.html:text/html}
}
@article{shimizu_lingam:_2014,
title = {{LiNGAM}: Non-Gaussian methods for estimating causal structures},
volume = {41},
shorttitle = {{LiNGAM}},
pages = {65--98},
number = {1},
journaltitle = {Behaviormetrika},
author = {Shimizu, Shohei},
date = {2014},
file = {Fulltext:/home/vcabeli/Zotero/storage/R7FIJLGR/Shimizu - 2014 - LiNGAM Non-Gaussian methods for estimating causal.pdf:application/pdf;Shimizu13BHMK.pdf:/home/vcabeli/Zotero/storage/VJLASTCA/Shimizu13BHMK.pdf:application/pdf;Snapshot:/home/vcabeli/Zotero/storage/S3ZVGXMA/ja.html:text/html}
}
@article{kalisch_package_2017,
title = {Package ‘pcalg’},
author = {Kalisch, Markus and Hauser, Alain and Maechler, Martin and Colombo, Diego and Entner, Doris and Hoyer, Patrik and Hyttinen, Antti and Peters, Jonas and Andri, Nicoletta and Perkovic, Emilija},
date = {2017}
}
@article{buhlmann_cam:_2014,
title = {{CAM}: Causal additive models, high-dimensional order search and penalized regression},
volume = {42},
issn = {0090-5364},
url = {http://arxiv.org/abs/1310.1533},
doi = {10.1214/14-AOS1260},
shorttitle = {{CAM}},
abstract = {We develop estimation for potentially high-dimensional additive structural equation models. A key component of our approach is to decouple order search among the variables from feature or edge selection in a directed acyclic graph encoding the causal structure. We show that the former can be done with nonregularized (restricted) maximum likelihood estimation while the latter can be efficiently addressed using sparse regression techniques. Thus, we substantially simplify the problem of structure search and estimation for an important class of causal models. We establish consistency of the (restricted) maximum likelihood estimator for low- and high-dimensional scenarios, and we also allow for misspecification of the error distribution. Furthermore, we develop an efficient computational algorithm which can deal with many variables, and the new method's accuracy and performance is illustrated on simulated and real data.},
pages = {2526--2556},
number = {6},
journaltitle = {The Annals of Statistics},
author = {Bühlmann, Peter and Peters, Jonas and Ernest, Jan},
urldate = {2018-02-06},
date = {2014-12},
eprinttype = {arxiv},
eprint = {1310.1533},
keywords = {Computer Science - Learning, Statistics - Machine Learning, Statistics - Methodology},
file = {arXiv\:1310.1533 PDF:/home/vcabeli/Zotero/storage/Y7JWLX7K/Bühlmann et al. - 2014 - CAM Causal additive models, high-dimensional orde.pdf:application/pdf;arXiv.org Snapshot:/home/vcabeli/Zotero/storage/RRIYZ24D/1310.html:text/html}
}
@article{kinney_equitability_2014,
title = {Equitability, mutual information, and the maximal information coefficient},
volume = {111},
rights = {© . Freely available online through the {PNAS} open access option.},
issn = {0027-8424, 1091-6490},
url = {http://www.pnas.org/content/111/9/3354},
doi = {10.1073/pnas.1309933111},
abstract = {How should one quantify the strength of association between two random variables without bias for relationships of a specific form? Despite its conceptual simplicity, this notion of statistical “equitability” has yet to receive a definitive mathematical formalization. Here we argue that equitability is properly formalized by a self-consistency condition closely related to Data Processing Inequality. Mutual information, a fundamental quantity in information theory, is shown to satisfy this equitability criterion. These findings are at odds with the recent work of Reshef et al. [Reshef {DN}, et al. (2011) Science 334(6062):1518–1524], which proposed an alternative definition of equitability and introduced a new statistic, the “maximal information coefficient” ({MIC}), said to satisfy equitability in contradistinction to mutual information. These conclusions, however, were supported only with limited simulation evidence, not with mathematical arguments. Upon revisiting these claims, we prove that the mathematical definition of equitability proposed by Reshef et al. cannot be satisfied by any (nontrivial) dependence measure. We also identify artifacts in the reported simulation evidence. When these artifacts are removed, estimates of mutual information are found to be more equitable than estimates of {MIC}. Mutual information is also observed to have consistently higher statistical power than {MIC}. We conclude that estimating mutual information provides a natural (and often practical) way to equitably quantify statistical associations in large datasets.},
pages = {3354--3359},
number = {9},
journaltitle = {Proceedings of the National Academy of Sciences},
shortjournal = {{PNAS}},
author = {Kinney, Justin B. and Atwal, Gurinder S.},
urldate = {2018-03-05},
date = {2014-03-04},
langid = {english},
pmid = {24550517},
keywords = {{BIC}},
file = {Full Text PDF:/home/vcabeli/Zotero/storage/LJIV8ALX/Kinney and Atwal - 2014 - Equitability, mutual information, and the maximal .pdf:application/pdf;Snapshot:/home/vcabeli/Zotero/storage/8YRS7XEH/3354.html:text/html}
}
@article{reshef_detecting_2011,
title = {Detecting Novel Associations in Large Datasets},
volume = {334},
issn = {0036-8075},
url = {https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3325791/},
doi = {10.1126/science.1205438},
abstract = {Identifying interesting relationships between pairs of variables in large datasets is increasingly important. Here, we present a measure of dependence for two-variable relationships: the maximal information coefficient ({MIC}). {MIC} captures a wide range of associations both functional and not, and for functional relationships provides a score that roughly equals the coefficient of determination (R2) of the data relative to the regression function. {MIC} belongs to a larger class of maximal information-based nonparametric exploration ({MINE}) statistics for identifying and classifying relationships. We apply {MIC} and {MINE} to datasets in global health, gene expression, major-league baseball, and the human gut microbiota, and identify known and novel relationships.},
pages = {1518--1524},
number = {6062},
journaltitle = {Science (New York, N.y.)},
shortjournal = {Science},
author = {Reshef, David N. and Reshef, Yakir A. and Finucane, Hilary K. and Grossman, Sharon R. and {McVean}, Gilean and Turnbaugh, Peter J. and Lander, Eric S. and Mitzenmacher, Michael and Sabeti, Pardis C.},
urldate = {2018-03-06},
date = {2011-12-16},
pmid = {22174245},
pmcid = {PMC3325791},
keywords = {{BIC}, binning},
file = {NIHMS358982-supplement-Supplemental_Figures_and_Tables.pdf:/home/vcabeli/Zotero/storage/5BZDJMRA/NIHMS358982-supplement-Supplemental_Figures_and_Tables.pdf:application/pdf;PubMed Central Full Text PDF:/home/vcabeli/Zotero/storage/5QMAPQEH/Reshef et al. - 2011 - Detecting Novel Associations in Large Datasets.pdf:application/pdf}
}
@article{gao_estimating_2017,
title = {Estimating Mutual Information for Discrete-Continuous Mixtures},
url = {http://arxiv.org/abs/1709.06212},
abstract = {Estimating mutual information from observed samples is a basic primitive, useful in several machine learning tasks including correlation mining, information bottleneck clustering, learning a Chow-Liu tree, and conditional independence testing in (causal) graphical models. While mutual information is a well-defined quantity in general probability spaces, existing estimators can only handle two special cases of purely discrete or purely continuous pairs of random variables. The main challenge is that these methods first estimate the (differential) entropies of X, Y and the pair (X;Y) and add them up with appropriate signs to get an estimate of the mutual information. These 3H-estimators cannot be applied in general mixture spaces, where entropy is not well-defined. In this paper, we design a novel estimator for mutual information of discrete-continuous mixtures. We prove that the proposed estimator is consistent. We provide numerical experiments suggesting superiority of the proposed estimator compared to other heuristics of adding small continuous noise to all the samples and applying standard estimators tailored for purely continuous variables, and quantizing the samples and applying standard estimators tailored for purely discrete variables. This significantly widens the applicability of mutual information estimation in real-world applications, where some variables are discrete, some continuous, and others are a mixture between continuous and discrete components.},
journaltitle = {{arXiv}:1709.06212 [cs, math]},
author = {Gao, Weihao and Kannan, Sreeram and Oh, Sewoong and Viswanath, Pramod},
urldate = {2018-03-15},
date = {2017-09-18},
eprinttype = {arxiv},
eprint = {1709.06212},
keywords = {Computer Science - Information Theory, Computer Science - Learning},
file = {arXiv\:1709.06212 PDF:/home/vcabeli/Zotero/storage/SWBN6MHG/Gao et al. - 2017 - Estimating Mutual Information for Discrete-Continu.pdf:application/pdf;arXiv.org Snapshot:/home/vcabeli/Zotero/storage/TLFB4AJV/1709.html:text/html}
}
@article{ross_mutual_2014,
title = {Mutual Information between Discrete and Continuous Data Sets},
volume = {9},
issn = {1932-6203},
url = {http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0087357},
doi = {10.1371/journal.pone.0087357},
abstract = {Mutual information ({MI}) is a powerful method for detecting relationships between data sets. There are accurate methods for estimating {MI} that avoid problems with “binning” when both data sets are discrete or when both data sets are continuous. We present an accurate, non-binning {MI} estimator for the case of one discrete data set and one continuous data set. This case applies when measuring, for example, the relationship between base sequence and gene expression level, or the effect of a cancer drug on patient survival time. We also show how our method can be adapted to calculate the Jensen–Shannon divergence of two or more data sets.},
pages = {e87357},
number = {2},
journaltitle = {{PLOS} {ONE}},
shortjournal = {{PLOS} {ONE}},
author = {Ross, Brian C.},
urldate = {2018-03-15},
date = {2014-02-19},
langid = {english},
keywords = {Entropy, Gene expression, Information theory, Nucleobases, Probability density, Probability distribution, Square waves, Statistical distributions},
file = {Full Text PDF:/home/vcabeli/Zotero/storage/N6AG8DA7/Ross - 2014 - Mutual Information between Discrete and Continuous.pdf:application/pdf;Snapshot:/home/vcabeli/Zotero/storage/KJE64WLI/article.html:text/html}
}
@article{tsagris_constraint-based_2018,
title = {Constraint-based causal discovery with mixed data},
pages = {1--12},
journaltitle = {International Journal of Data Science and Analytics},
author = {Tsagris, Michail and Borboudakis, Giorgos and Lagani, Vincenzo and Tsamardinos, Ioannis},
date = {2018},
keywords = {{MXM}},
file = {Fulltext:/home/vcabeli/Zotero/storage/9GUPLKMY/Tsagris et al. - 2018 - Constraint-based causal discovery with mixed data.pdf:application/pdf;Snapshot:/home/vcabeli/Zotero/storage/4D9D3S2S/s41060-018-0097-y.html:text/html}
}
@article{sedgewick_mixed_2018,
title = {Mixed graphical models for integrative causal analysis with application to chronic lung disease diagnosis and prognosis},
journaltitle = {Bioinformatics},
author = {Sedgewick, Andrew J. and Buschur, Kristina and Shi, Ivy and Ramsey, Joseph D. and Raghu, Vineet K. and Manatakis, Dimitris V. and Zhang, Yingze and Bon, Jessica and Chandra, Divay and Karoleski, Chad},
date = {2018},
file = {Sedgewick et al. - 2018 - Mixed graphical models for integrative causal anal.pdf:/home/vcabeli/Zotero/storage/55PTS4DN/Sedgewick et al. - 2018 - Mixed graphical models for integrative causal anal.pdf:application/pdf;Snapshot:/home/vcabeli/Zotero/storage/EKX3ASUH/5091182.html:text/html}
}
@book{cover_elements_2012,
title = {Elements of information theory},
publisher = {John Wiley \& Sons},
author = {Cover, Thomas M. and Thomas, Joy A.},
date = {2012}
}
@article{albanese_minerva_2013,
title = {Minerva and minepy: a C engine for the {MINE} suite and its R, Python and {MATLAB} wrappers},
volume = {29},
issn = {1367-4811},
doi = {10.1093/bioinformatics/bts707},
shorttitle = {Minerva and minepy},
abstract = {We introduce a novel implementation in {ANSI} C of the {MINE} family of algorithms for computing maximal information-based measures of dependence between two variables in large datasets, with the aim of a low memory footprint and ease of integration within bioinformatics pipelines. We provide the libraries minerva (with the R interface) and minepy for Python, {MATLAB}, Octave and C++. The C solution reduces the large memory requirement of the original Java implementation, has good upscaling properties and offers a native parallelization for the R interface. Low memory requirements are demonstrated on the {MINE} benchmarks as well as on large ( = 1340) microarray and Illumina {GAII} {RNA}-seq transcriptomics datasets.
{AVAILABILITY} {AND} {IMPLEMENTATION}: Source code and binaries are freely available for download under {GPL}3 licence at http://minepy.sourceforge.net for minepy and through the {CRAN} repository http://cran.r-project.org for the R package minerva. All software is multiplatform ({MS} Windows, Linux and {OSX}).},
pages = {407--408},
number = {3},
journaltitle = {Bioinformatics (Oxford, England)},
shortjournal = {Bioinformatics},
author = {Albanese, Davide and Filosi, Michele and Visintainer, Roberto and Riccadonna, Samantha and Jurman, Giuseppe and Furlanello, Cesare},
date = {2013-02-01},
pmid = {23242262},
keywords = {Algorithms, Computational Biology, Data Mining, Gene Expression Profiling, Metagenome, Software},
file = {Texte intégral:/home/vcabeli/Zotero/storage/TTGAWDIJ/Albanese et al. - 2013 - Minerva and minepy a C engine for the MINE suite .pdf:application/pdf}
}
@article{lizier_jidt_2014,
title = {{JIDT}: An information-theoretic toolkit for studying the dynamics of complex systems},
volume = {1},
shorttitle = {{JIDT}},
pages = {11},
journaltitle = {Frontiers in Robotics and {AI}},
author = {Lizier, Joseph T.},
date = {2014},
file = {Full Text:/home/vcabeli/Zotero/storage/UYEVK5FZ/full.html:text/html}
}