Gradient descent in hyperbolic space

arXiv1805.08207MaRDI QIDQ6301903FDOQ6301903

Authors: Benjamin Wilson, Matthias Leimeister 

Publication date: 18 May 2018

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 Fr'echet mean (i.e. barycentre) of points in hyperbolic space.

Has companion code repository: https://github.com/lateral/geodesic-poincare-embeddings

This page was built for publication: Gradient descent in hyperbolic space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6301903)