@@ -28,7 +28,7 @@ Recently, deep learning has been applied to non-structured 3D geometries as for
Recent work also includes methods for quantifying uncertainty in manifold-valued predictors, resulting in prbabilistic algorithms for both manifold learning and regression when the data at hand is known to satisfy nonlinear constraints or invariances encoded by a Riemannian manifold structure.
We develop methods for analyzing data that respects known invariances or constraints, for example encoded in a Riemannian manifold structure (Mallasto et al, CVPR'18 and AISTATS'19).
