From the Greene--Wu Convolution to Gradient Estimation over Riemannian Manifolds
This work addresses gradient estimation challenges in non-Euclidean machine learning, though it appears incremental as it builds on existing convolution theory.
The paper studied the Greene-Wu convolution on Riemannian manifolds, deriving a formula linking space curvature to function curvature and introducing a new gradient estimation method for non-Euclidean machine learning problems.
Over a complete Riemannian manifold of finite dimension, Greene and Wu introduced a convolution, known as Greene-Wu (GW) convolution. In this paper, we study properties of the GW convolution and apply it to non-Euclidean machine learning problems. In particular, we derive a new formula for how the curvature of the space would affect the curvature of the function through the GW convolution. Also, following the study of the GW convolution, a new method for gradient estimation over Riemannian manifolds is introduced.