pith. sign in

arxiv: 1403.0740 · v2 · pith:EM3YSP7Xnew · submitted 2014-03-04 · 🧮 math.ST · stat.TH

On the Information-theoretic Limits of Graphical Model Selection for Gaussian Time Series

classification 🧮 math.ST stat.TH
keywords information-theoreticprocessboundgaussianlimitsmodelschemeselection
0
0 comments X
read the original abstract

We consider the problem of inferring the conditional independence graph (CIG) of a multivariate stationary dicrete-time Gaussian random process based on a finite length observation. Using information-theoretic methods, we derive a lower bound on the error probability of any learning scheme for the underlying process CIG. This bound, in turn, yields a minimum required sample-size which is necessary for any algorithm regardless of its computational complexity, to reliably select the true underlying CIG. Furthermore, by analysis of a simple selection scheme, we show that the information-theoretic limits can be achieved for a subclass of processes having sparse CIG. We do not assume a parametric model for the observed process, but require it to have a sufficiently smooth spectral density matrix (SDM).

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.