A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization
From MaRDI portal
Publication:6327779
arXiv1910.10782MaRDI QIDQ6327779FDOQ6327779
Authors: Foivos Alimisis, Gary Bécigneul 
Publication date: 23 October 2019
Abstract: We propose a novel second-order ODE as the continuous-time limit of a Riemannian accelerated gradient-based method on a manifold with curvature bounded from below. This ODE can be seen as a generalization of the ODE derived for Euclidean spaces, and can also serve as an analysis tool. We study the convergence behavior of this ODE for different classes of functions, such as geodesically convex, strongly-convex and weakly-quasi-convex. We demonstrate how such an ODE can be discretized using a semi-implicit and Nesterov-inspired numerical integrator, that empirically yields stable algorithms which are faithful to the continuous-time analysis and exhibit accelerated convergence.
Has companion code repository: https://github.com/aorvieto/riemann-continuous
This page was built for publication: A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6327779)
