Voxelwise encoding models with non-spherical multivariate normal priors (Nunez-Elizalde, Huth & Gallant, NeuroImage, 2019)
August 15, 2019
Ridge regression assumes a spherical Gaussian prior with equal variance for all model parameters, but this is not always appropriate. This paper shows how non-spherical priors via Tikhonov regression can improve encoding models. A key application is banded ridge regression, which assigns a separate regularization parameter to each feature space and provides substantially better prediction accuracy when combining multiple feature spaces.