Riemannian Acceleration with Preconditioning for symmetric eigenvalue problems
share
In this paper, we propose a Riemannian Acceleration with Preconditioning (RAP) for symmetric eigenvalue problems, which is one of the most important geodesically convex optimization problem on Riemannian manifold, and obtain the acceleration. Firstly, the preconditioning for symmetric eigenvalue problems from the Riemannian manifold viewpoint is discussed. In order to obtain the local geodesic convexity, we develop the leading angle to measure the quality of the preconditioner for symmetric eigenvalue problems. A new Riemannian acceleration, called Locally Optimal Riemannian Accelerated Gradient (LORAG) method, is proposed to overcome the local geodesic convexity for symmetric eigenvalue problems. With similar techniques for RAGD and analysis of local convex optimization in Euclidean space, we analyze the convergence of LORAG. Incorporating the local geodesic convexity of symmetric eigenvalue problems under preconditioning with the LORAG, we propose the Riemannian Acceleration with Preconditioning (RAP) and prove its acceleration. Additionally, when the Schwarz preconditioner, especially the overlapping or non-overlapping domain decomposition method, is applied for elliptic eigenvalue problems, we also obtain the rate of convergence as 1-Cκ^-1/2, where C is a constant independent of the mesh sizes and the eigenvalue gap, κ=κ_νλ_2/(λ_2-λ_1), κ_ν is the parameter from the stable decomposition, λ_1 and λ_2 are the smallest two eigenvalues of the elliptic operator. Numerical results show the power of Riemannian acceleration and preconditioning.
READ FULL TEXT