6533b826fe1ef96bd1284d69

RESEARCH PRODUCT

Cyclic coordinate for penalized Gaussian graphical models with symmetry restriction

A AbbruzzoL AugugliaroA MineoE Wit

subject

Factorial dynamic Gaussian graphical models Gaussian graphical models graphical lasso cyclic coordinate descent methodsSettore SECS-S/01 - Statistica

description

In this paper we propose two efficient cyclic coordinate algorithms to estimate structured concentration matrix in penalized Gaussian graphical models. Symmetry restrictions on the concentration matrix are particularly useful to reduce the number of parameters to be estimated and to create specific structured graphs. The penalized Gaussian graphical models are suitable for high-dimensional data.

http://hdl.handle.net/10447/96091