CovNet: Covariance Networks for Functional Data on Multidimensional Domains
This addresses a bottleneck in functional data analysis for researchers dealing with high-dimensional domains, offering a novel computational tool with broad applicability.
The paper tackles the computational and statistical challenges of covariance estimation for functional data over multidimensional domains by introducing Covariance Networks (CovNet), a universal model that approximates any covariance efficiently and allows closed-form eigendecomposition, with demonstrated consistency and convergence rates validated through simulations and fMRI data.
Covariance estimation is ubiquitous in functional data analysis. Yet, the case of functional observations over multidimensional domains introduces computational and statistical challenges, rendering the standard methods effectively inapplicable. To address this problem, we introduce "Covariance Networks" (CovNet) as a modeling and estimation tool. The CovNet model is "universal" - it can be used to approximate any covariance up to desired precision. Moreover, the model can be fitted efficiently to the data and its neural network architecture allows us to employ modern computational tools in the implementation. The CovNet model also admits a closed-form eigendecomposition, which can be computed efficiently, without constructing the covariance itself. This facilitates easy storage and subsequent manipulation of a covariance in the context of the CovNet. We establish consistency of the proposed estimator and derive its rate of convergence. The usefulness of the proposed method is demonstrated by means of an extensive simulation study and an application to resting state fMRI data.