Representation and reconstruction of covariance operators in linear inverse problems

Abstract

We introduce a framework for the reconstruction and representation of functions in a setting where these objects cannot be directly observed, but only indirect and noisy measurements are available, namely an inverse problem setting. The proposed methodology can be applied either to the analysis of indirectly observed functional images or to the associated covariance operators, representing second-order information, and thus lying on a non-Euclidean space. To deal with the ill-posedness of the inverse problem, we exploit the spatial structure of the sample data by introducing a flexible regularizing term embedded in the model. Thanks to its efficiency, the proposed model is applied to MEG data, leading to a novel approach to the investigation of functional connectivity.

arXiv comment40 pages

References in corpus (10)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• A Review of Convolutional Neural Networks for Inverse Problems in Imaging
• Sparsity-Cognizant Total Least-Squares for Perturbed Compressive Sampling
• Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging
• Common functional principal components
• Functional principal components analysis via penalized rank one approximation
• Smooth Principal Component Analysis over two-dimensional manifolds with an application to Neuroimaging
• On the sample covariance matrix estimator of reduced effective rank population matrices, with applications to fPCA
• Sampled forms of functional PCA in reproducing kernel Hilbert spaces
• A two-way regularization method for MEG source reconstruction