Year: 2018
Type: preprint
Abstract: Gradient descent generalises naturally to Riemannian manifolds, and to hyperbolic $n$-space, in particular. Namely, having calculated the gradient at the point on the manifold representing the model parameters, the updated point is obtained by travelling along the geodesic passing in the direction of the gradient. Some recent works employing optimisation in hyperbolic space have not attempted this procedure, however, employing instead various approximations to avoid a calculation that was considered to be too complicated. In this tutorial, we demonstrate that in the hyperboloid model of hyperbolic space, the necessary calculations to perform gradient descent are in fact straight-forward. The advantages of the approach are then both illustrated and quantified for the optimisation problem of computing the Fréchet mean (i.e. barycentre) of points in hyperbolic space.
Source: arXiv (Cornell University)
Authors: Wilson, Benjamin, Leimeister, Matthias
Language: English
Subfield: Applied Mathematics
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2803760543