MATHEMATICAL ENGINEERING TECHNICAL REPORTS A Structural Model on a Hypercube Represented by Optimal Transport

We propose a flexible statistical model for high-dimensional quantitative data on a hypercube. Our model, called the structural gradient model (SGM), is based on a one-to-one map on the hypercube that is a solution for an optimal transport problem. As we show with many examples, SGM can describe various dependence structures including correlation and heteroscedasticity. The maximum likelihood estimation of SGM is effectively solved by the determinant-maximization programming. In particular, a lasso-type estimation is available by adding constraints. SGM is compared with graphical Gaussian models and mixture models.

[1]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1972 .

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

[3]  D. Edwards.  Introduction to graphical modelling , 1995 .

[4]  H. Halkin,et al.  Determinants of the renal clearance of digoxin , 1975, Clinical pharmacology and therapeutics.

[5]  Y. Brenier.  Polar Factorization and Monotone Rearrangement of Vector-Valued Functions , 1991 .

[6]  R. Nelsen.  An Introduction to Copulas , 1998 .

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

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

[9]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

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

[11]  C. Villani.  Topics in Optimal Transportation , 2003 .

[12]  Wenjiang J. Fu,et al.  Asymptotics for lasso-type estimators , 2000 .

[13]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[14]  R. Christensen.  Introduction to Graphical Modeling , 2001 .

[15]  Luis A. Caffarelli,et al.  Monotonicity Properties of Optimal Transportation¶and the FKG and Related Inequalities , 2000 .

[16]  J. Fernández-Durán,et al.  Circular Distributions Based on Nonnegative Trigonometric Sums , 2004, Biometrics.

[17]  Stephen P. Boyd,et al.  Determinant Maximization with Linear Matrix Inequality Constraints , 1998, SIAM J. Matrix Anal. Appl..

[18]  Florentina Bunea,et al.  Sparse Density Estimation with l1 Penalties , 2007, COLT.

[19]  MATHEMATICAL ENGINEERING TECHNICAL REPORTS Parametric modeling based on the gradient maps of convex functions , 2006 .

[20]  Alexandre d'Aspremont,et al.  Model Selection Through Sparse Max Likelihood Estimation Model Selection Through Sparse Maximum Likelihood Estimation for Multivariate Gaussian or Binary Data , 2022 .

[21]  T. Sei.  Gradient modeling for multivariate quantitative data , 2011 .

[22]  丸山 徹.  Convex Analysisの二,三の進展について , 1977 .

[23]  Arkadi Nemirovski,et al.  Robust Convex Optimization , 1998, Math. Oper. Res..

[24]  R. McCann.  Existence and uniqueness of monotone measure-preserving maps , 1995 .