We propose a fast, simple and robust algorithm for computing shortest paths and distances on Riemannian manifolds learned from data. This amounts to solving a system of ordinary differential equations (ODEs) subject to boundary conditions. Here standard solvers perform poorly because they require well-behaved Jacobians of the ODE, and usually, manifolds learned from data imply unstable and ill-conditioned Jacobians. Instead, we propose a fixed-point iteration scheme for solving the ODE that avoids Jacobians. This enhances the stability of the solver, while reduces the computational cost. In experiments involving both Riemannian metric learning and deep generative models we demonstrate significant improvements in speed and stability over both general-purpose state-of-the-art solvers as well as over specialized solvers.
|Title of host publication||Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics|
|Publication status||Published - 2019|
|Event||22nd International Conference on Artificial Intelligence and Statistics - LOISIR Hotel, Naha, Japan|
Duration: 16 Apr 2019 → 18 Apr 2019
|Conference||22nd International Conference on Artificial Intelligence and Statistics|
|Period||16/04/2019 → 18/04/2019|