Stein's Method of Moments on the Sphere

A Fischer, RE Gaunt, Y Swan - arXiv preprint arXiv:2407.02299, 2024 - arxiv.org
We use Stein characterizations to obtain new moment-type estimators for the parameters of
three classical spherical distributions (namely the Fisher-Bingham, the von Mises-Fisher …

Equivariance allows handling multiple nuisance variables when analyzing pooled neuroimaging datasets

VS Lokhande, R Chakraborty… - Proceedings of the …, 2022 - openaccess.thecvf.com
Pooling multiple neuroimaging datasets across institutions often enables significant
improvements in statistical power when evaluating associations (eg, between risk factors …

Solving the reconstruction-generation trade-off: Generative model with implicit embedding learning

C Geng, J Wang, L Chen, Z Gao - Neurocomputing, 2023 - Elsevier
Abstract Variational Autoencoder (VAE) and Generative adversarial network (GAN) are two
classic generative models that generate realistic data from a predefined prior distribution …