Global q-superlinear convergence of the infinite-dimensional Newton's method for the regularized p-Stokes equations
share
The motion of glaciers can be simulated with the p-Stokes equations. We present an algorithm that solves these equations faster than the Picard iteration. We do that by proving q-superlinear global convergence of the infinite-dimensional Newton's method with Armijo step sizes to the solution of these equations. We only have to add an arbitrarily small diffusion term for this convergence result. We also consider approximations of exact step sizes. Exact step sizes are possible because we reformulate the problem as minimizing a convex functional. Next, we prove that the additional diffusion term only causes minor differences in the solution compared to the original p-Stokes equations. Finally, we test our algorithms on a reformulation of the experiment ISMIP-HOM B. The approximation of exact step sizes for the Picard iteration and Newton's method is superior in the experiment compared to the Picard iteration. Also, Newton's method with Armijo step sizes converges faster than the Picard iteration. However, the reached accuracy of Newton's method with Armijo step sizes depends more on the resolution of the domain.
READ FULL TEXT
