Geodesic Convexity and Covariance Estimation
Author:
- 11 September 2012
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 60 (12) , 6182-6189
Abstract
Geodesic convexity is a generalization of classical convexity which guarantees that all local minima of g-convex functions are globally optimal. We consider g-convex functions with positive definite matrix variables, and prove that Kronecker products, and logarithms of determinants are g-convex. We apply these results to two modern covariance estimation problems: robust estimation in scaled Gaussian distributions, and Kronecker structured models. Maximum likelihood estimation in these settings involves non-convex minimizations. We show that these problems are in fact g-convex. This leads to straight forward analysis, allows the use of standard optimization methods and paves the road to various extensions via additional g-convex regularization.Keywords
This publication has 39 references indexed in Scilit:
- Comment on “Models with a Kronecker Product Covariance Structure: Estimation and Testing” by M. S. Srivastava, T. von Rosen, and D. von Rosen, Mathematical Methods of Statistics, 17 (2008), pp. 357–370Mathematical Methods of Statistics, 2010
- Riemannian Metric and Geometric Mean for Positive Semidefinite Matrices of Fixed RankSIAM Journal on Matrix Analysis and Applications, 2010
- Are a set of microarrays independent of each other?The Annals of Applied Statistics, 2009
- Covariance Structure Maximum-Likelihood Estimates in Compound Gaussian Noise: Existence and Algorithm AnalysisIEEE Transactions on Signal Processing, 2007
- Covariance, subspace, and intrinsic Crame/spl acute/r-Rao boundsIEEE Transactions on Signal Processing, 2005
- A Differential Geometric Approach to the Geometric Mean of Symmetric Positive-Definite MatricesSIAM Journal on Matrix Analysis and Applications, 2005
- Convex Optimization2004
- A stochastic MIMO radio channel model with experimental validationIEEE Journal on Selected Areas in Communications, 2002
- Generalized arcwise-connected functions and characterizations of local-global minimum propertiesJournal of Optimization Theory and Applications, 1980
- On generalized means and generalized convex functionsJournal of Optimization Theory and Applications, 1977