On graphical models and convex geometry

We introduce a mixture-model of beta distributions to identify significant correlations among P predictors when P is large. The method relies on theorems in convex geometry, which we use to show how to control the error rate of edge detection in graphical models. Our ‘betaMix’ method does not require any assumptions about the network structure, nor does it assume that the network is sparse. The results in this article hold for a wide class of data generating distributions that include light-tailed and heavy-tailed spherically symmetric distributions.

[1]  P. C. Kainen,et al.  Quasiorthogonal Dimension , 2020, Studies in Computational Intelligence.

[2]  Antonio Reverter,et al.  Combining partial correlation and an information theory approach to the reversed engineering of gene co-expression networks , 2008, Bioinform..

[3]  Robert Tibshirani,et al.  Sparse regression and marginal testing using cluster prototypes. , 2015, Biostatistics.

[4]  Haim Bar,et al.  A mixture model to detect edges in sparse co-expression graphs with an application for comparing breast cancer subtypes. , 2018, PloS one.

[5]  Levent Tunçel,et al.  Optimization algorithms on matrix manifolds , 2009, Math. Comput..

[6]  A. Hero,et al.  Large-Scale Correlation Screening , 2011, 1102.1204.

[7]  T. Cai,et al.  Two-Sample Covariance Matrix Testing and Support Recovery in High-Dimensional and Sparse Settings , 2013 .

[8]  Kai Zhang,et al.  Spherical Cap Packing Asymptotics and Rank-Extreme Detection , 2015, IEEE Transactions on Information Theory.

[9]  Avrim Blum,et al.  Foundations of Data Science , 2020 .

[10]  P. Bickel,et al.  Covariance regularization by thresholding , 2009, 0901.3079.

[11]  Adam J. Rothman,et al.  Sparse estimation of large covariance matrices via a nested Lasso penalty , 2008, 0803.3872.

[12]  Eugene P. Wigner,et al.  Formulas and Theorems for the Special Functions of Mathematical Physics , 1966 .

[13]  Bradley Efron,et al.  Minimum volume confidence regions for a multivariate normal mean vector , 2006 .

[14]  S. Geer,et al.  On asymptotically optimal confidence regions and tests for high-dimensional models , 2013, 1303.0518.

[15]  P. Koev,et al.  On the largest principal angle between random subspaces , 2006 .

[16]  Jianqing Fan,et al.  Distributions of angles in random packing on spheres , 2013, J. Mach. Learn. Res..

[17]  M. Yuan,et al.  Model selection and estimation in the Gaussian graphical model , 2007 .

[18]  J. S. Marron,et al.  Geometric representation of high dimension, low sample size data , 2005 .

[19]  G. S. Watson.  Statistics on Spheres , 1983 .

[20]  N. J. A. Sloane,et al.  Packing Lines, Planes, etc.: Packings in Grassmannian Spaces , 1996, Exp. Math..

[21]  T. Cai,et al.  Limiting laws of coherence of random matrices with applications to testing covariance structure and construction of compressed sensing matrices , 2011, 1102.2925.

[22]  T. Tony Cai,et al.  Phase transition in limiting distributions of coherence of high-dimensional random matrices , 2011, J. Multivar. Anal..

[23]  Jinchi Lv,et al.  Impacts of high dimensionality in finite samples , 2013, 1311.2742.

[24]  Kathryn Roeder,et al.  TESTING HIGH-DIMENSIONAL COVARIANCE MATRICES, WITH APPLICATION TO DETECTING SCHIZOPHRENIA RISK GENES. , 2016, The annals of applied statistics.

[25]  P. Bickel,et al.  Sparsity and the Possibility of Inference , 2008 .

[26]  Peter Bühlmann,et al.  High-Dimensional Statistics with a View Toward Applications in Biology , 2014 .

[27]  P. Frankl,et al.  Some geometric applications of the beta distribution , 1990 .

[28]  K. Ball.  An Elementary Introduction to Modern Convex Geometry , 1997 .

[29]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[30]  J WainwrightMartin.  Sharp thresholds for high-dimensional and noisy sparsity recovery using l1-constrained quadratic programming (Lasso) , 2009 .

[31]  Alan Edelman,et al.  The efficient evaluation of the hypergeometric function of a matrix argument , 2006, Math. Comput..

[32]  K. Khare,et al.  A convex pseudolikelihood framework for high dimensional partial correlation estimation with convergence guarantees , 2013, 1307.5381.

[33]  Martin T. Wells,et al.  A Scalable Empirical Bayes Approach to Variable Selection , 2015, 1510.03781.

[34]  A. James.  Normal Multivariate Analysis and the Orthogonal Group , 1954 .

[35]  R. Muirhead.  Aspects of Multivariate Statistical Theory , 1982, Wiley Series in Probability and Statistics.

[36]  N. Meinshausen,et al.  High-dimensional graphs and variable selection with the Lasso , 2006, math/0608017.

[37]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the graphical lasso. , 2008, Biostatistics.

[38]  Pei Wang,et al.  Partial Correlation Estimation by Joint Sparse Regression Models , 2008, Journal of the American Statistical Association.

[39]  H. Hilhorst,et al.  Metabolomic analysis of tomato seed germination , 2017, Metabolomics.

[40]  Gregory Piatetsky-Shapiro,et al.  High-Dimensional Data Analysis: The Curses and Blessings of Dimensionality , 2000 .

[41]  Adam J. Rothman,et al.  Sparse permutation invariant covariance estimation , 2008, 0801.4837.

[42]  Alfred O. Hero,et al.  Foundational Principles for Large-Scale Inference: Illustrations Through Correlation Mining , 2015, Proceedings of the IEEE.

[43]  M. Basseville.  Distance measures for signal processing and pattern recognition , 1989 .

[44]  Kevin Baker,et al.  Classification of radar returns from the ionosphere using neural networks , 1989 .

[45]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[46]  Gábor Csárdi,et al.  The igraph software package for complex network research , 2006 .

[47]  David I. Warton,et al.  Penalized Normal Likelihood and Ridge Regularization of Correlation and Covariance Matrices , 2008 .