On the two-step estimation of the cross-power spectrum for dynamical linear inverse problems

DOI10.1088/1361-6420/AB67DCzbMATH Open1467.92115arXiv1909.01266OpenAlexW2998960428MaRDI QIDQ5000584FDOQ5000584

Authors: Elisabetta Vallarino, Sara Sommariva, Michele Piana, Alberto Sorrentino 

Publication date: 14 July 2021

Published in: Inverse Problems (Search for Journal in Brave)

Abstract: We consider the problem of reconstructing the cross--power spectrum of an unobservable multivariate stochatic process from indirect measurements of a second multivariate stochastic process, related to the first one through a linear operator. In the two--step approach, one would first compute a regularized reconstruction of the unobservable signal, and then compute an estimate of its cross--power spectrum from the regularized solution. We investigate whether the optimal regularization parameter for reconstruction of the signal also gives the best estimate of the cross--power spectrum. We show that the answer depends on the regularization method, and specifically we prove that, under a white Gaussian assumption: (i) when regularizing with truncated SVD the optimal parameter is the same; (ii) when regularizing with the Tikhonov method, the optimal parameter for the cross--power spectrum is lower than half the optimal parameter for the signal. We also provide evidence that a one--step approach would likely have better mathematical properties of the two--step approach. Our results apply particularly to the brain connectivity estimation from magneto/electro-encephalographic recordings and provide a formal interpretation of recent empirical results.

Full work available at URL: https://arxiv.org/abs/1909.01266

Recommendations

• On two-spectra inverse problems
• Relation between data of dynamic and spectral inverse problems
• Spectral estimation and inverse initial boundary value problems
• Inverse spectral problems of the theory of identification of linear dynamic systems
• On relations between spectral and dynamical inverse data
• A two-stage method for nonlinear inverse problems
• A Numerical Method for the Inverse Stochastic Spectrum Problem
• Two-step regularization methods for linear inverse problems
• Sturm-Liouville inverse spectral problem in the realization of linear dynamic systems

zbMATH Keywords

functional connectivityregularization theorym/EEGmultivariate stochastic processescross-power spectrummagneto/electro-encephalography

Mathematics Subject Classification ID

Biomedical imaging and signal processing (92C55) Inverse problems for PDEs (35R30)

Cites Work

• Measurement of Linear Dependence and Feedback Between Multiple Time Series
• Partial directed coherence: a new concept in neural structure determination
• Inverse modeling for MEG/EEG data
• A hierarchical Krylov-Bayes iterative inverse solver for MEG with physiological preconditioning
• A hierarchical Bayesian perspective on majorization-minimization for non-convex sparse regression: application to M/EEG source imaging
• Evaluation of connectivity estimates using spiking neuronal network models

Uses Software

• UTV
• MNE

This page was built for publication: On the two-step estimation of the cross-power spectrum for dynamical linear inverse problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5000584)