Frobenius Norm Regularization for the Multivariate Von Mises Distribution

Penalizing the model complexity is necessary to avoid overfitting when the number of data samples is low with respect to the number of model parameters. In this paper, we introduce a penalization term that places an independent prior distribution for each parameter of the multivariate von Mises distribution. We also propose a circular distance that can be used to estimate the Kullback–Leibler divergence between any two circular distributions as goodness‐of‐fit measure. We compare the resulting regularized von Mises models on synthetic data and real neuroanatomical data to show that the distribution fitted using the penalized estimator generally achieves better results than nonpenalized multivariate von Mises estimator.

[1]  Claus Bahlmann,et al.  Directional features in online handwriting recognition , 2006, Pattern Recognit..

[2]  Modeling farmer adaptations to climate change in South America: a micro-behavioral economic perspective , 2016, Environmental and Ecological Statistics.

[3]  Fernando Pérez-Cruz,et al.  Kullback-Leibler divergence estimation of continuous distributions , 2008, 2008 IEEE International Symposium on Information Theory.

[4]  G. Ascoli,et al.  NeuroMorpho.Org: A Central Resource for Neuronal Morphologies , 2007, The Journal of Neuroscience.

[5]  Hetunandan Kamisetty,et al.  The von Mises Graphical Model: Regularized Structure and Parameter Learning (CMU-CS-11-129/CMU-CB-11-101) , 2011 .

[6]  Harshinder Singh,et al.  Probabilistic model for two dependent circular variables , 2002 .

[7]  R. Fisher.  Dispersion on a sphere , 1953, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[8]  Rita Cucchiara,et al.  People Orientation Recognition by Mixtures of Wrapped Distributions on Random Trees , 2012, ECCV.

[9]  Kanti V. Mardia,et al.  A multivariate von mises distribution with applications to bioinformatics , 2008 .

[10]  Mohd Talib Latif,et al.  Fitting a mixture of von Mises distributions in order to model data on wind direction in Peninsular Malaysia , 2013 .

[11]  N. Fisher,et al.  Efficient Simulation of the von Mises Distribution , 1979 .

[12]  Kanti V. Mardia,et al.  Mixtures of concentrated multivariate sine distributions with applications to bioinformatics , 2012 .

[13]  F. Lagona.  Regression analysis of correlated circular data based on the multivariate von Mises distribution , 2016, Environmental and Ecological Statistics.

[14]  Su-In Lee,et al.  Learning graphical models with hubs , 2014, J. Mach. Learn. Res..

[15]  S. R. Jammalamadaka,et al.  Directional Statistics, I , 2011 .

[16]  Michael I. Jordan,et al.  An asymptotic analysis of generative, discriminative, and pseudolikelihood estimators , 2008, ICML '08.

[17]  J. Jacobs,et al.  Regional dendritic and spine variation in human cerebral cortex: a quantitative golgi study. , 2001, Cerebral cortex.

[18]  Shogo Kato,et al.  An extended family of circular distributions related to wrapped Cauchy distributions via Brownian motion , 2013, 1302.0098.

[19]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[20]  A. Borst.  The theoretical foundation of dendritic function edited by I. Segev, J. Rinzel and G.M. Shepherd, The MIT Press, 1995. $55.00 (vii + 465 pages) ISBN 0 262 19356 6 , 1995, Trends in Neurosciences.

[21]  S. R. Jammalamadaka,et al.  The generalized von Mises distribution , 2007 .

[22]  Concha Bielza,et al.  Regularized Multivariate von Mises Distribution , 2015, CAEPIA.

[23]  J. Besag.  Statistical Analysis of Non-Lattice Data , 1975 .

[24]  H. Qi,et al.  An augmented Lagrangian dual approach for the H-weighted nearest correlation matrix problem , 2011 .

[25]  A. Gelfand,et al.  Directional data analysis under the general projected normal distribution. , 2013, Statistical methodology.

[26]  A. Messac,et al.  A Multivariate and Multimodal Wind Distribution model , 2013 .

[27]  James G. King,et al.  Reconstruction and Simulation of Neocortical Microcircuitry , 2015, Cell.

[28]  Nicholas I. Fisher,et al.  Statistical Analysis of Circular Data , 1993 .

[29]  Inderjit S. Dhillon,et al.  Clustering on the Unit Hypersphere using von Mises-Fisher Distributions , 2005, J. Mach. Learn. Res..

[30]  Daniel T. Haydon,et al.  Assessing the impact of marine wind farms on birds through movement modelling , 2012, Journal of The Royal Society Interface.

[31]  F. Breidt,et al.  The General Projected Normal Distribution of Arbitrary Dimension: Modeling and Bayesian Inference , 2017 .

[32]  James G. King,et al.  The neocortical microcircuit collaboration portal: a resource for rat somatosensory cortex , 2015, Front. Neural Circuits.

[33]  Anja Vogler,et al.  An Introduction to Multivariate Statistical Analysis , 2004 .

[34]  Jeffrey A. Fessler.  Mean and variance of implicitly defined biased estimators (such as penalized maximum likelihood): applications to tomography , 1996, IEEE Trans. Image Process..

[35]  C. Anderson‐Cook,et al.  An Introduction to Multivariate Statistical Analysis (3rd ed.) (Book) , 2004 .

[36]  Kanti V. Mardia,et al.  Some Fundamental Properties of a Multivariate von Mises Distribution , 2011, 1109.6042.

[37]  Jorge Nocedal,et al.  Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization , 1997, TOMS.

[38]  John K Kruschke,et al.  Bayesian data analysis. , 2010, Wiley interdisciplinary reviews. Cognitive science.

[39]  P. Bickel,et al.  Regularized estimation of large covariance matrices , 2008, 0803.1909.

[40]  J. DeFelipe,et al.  Chronic cocaine treatment alters dendritic arborization in the adult motor cortex through a CB1 cannabinoid receptor–dependent mechanism , 2007, Neuroscience.

[41]  Ramon C. Littell,et al.  Projected multivariate linear models for directional data , 1998 .

[42]  A. Brix.  Bayesian Data Analysis, 2nd edn , 2005 .