From geodesic extrapolation to a variational BDF2 scheme for Wasserstein gradient flows

09/29/2022
by   Andrea Natale, et al.
0

We introduce a time discretization for Wasserstein gradient flows based on the classical Backward Differentiation Formula of order two. The main building block of the scheme is the notion of geodesic extrapolation in the Wasserstein space, which in general is not uniquely defined. We propose several possible definitions for such an operation, and we prove convergence of the resulting scheme to the limit PDE, in the case of the Fokker-Planck equation. For a specific choice of extrapolation we also prove a more general result, that is convergence towards EVI flows. Finally, we propose a variational finite volume discretization of the scheme which numerically achieves second order accuracy in both space and time.

READ FULL TEXT
research
07/18/2019

A variational finite volume scheme for Wasserstein gradient flows

We propose a variational finite volume scheme to approximate the solutio...
research
01/20/2020

TPFA Finite Volume Approximation of Wasserstein Gradient Flows

Numerous infinite dimensional dynamical systems arising in different fie...
research
07/03/2019

Fisher information regularization schemes for Wasserstein gradient flows

We propose a variational scheme for computing Wasserstein gradient flows...
research
10/06/2020

Optimizing Deep Neural Networks via Discretization of Finite-Time Convergent Flows

In this paper, we investigate in the context of deep neural networks, th...
research
02/18/2020

A Wasserstein Minimum Velocity Approach to Learning Unnormalized Models

Score matching provides an effective approach to learning flexible unnor...
research
01/27/2023

Neural Wasserstein Gradient Flows for Maximum Mean Discrepancies with Riesz Kernels

Wasserstein gradient flows of maximum mean discrepancy (MMD) functionals...
research
09/16/2022

Solving Fredholm Integral Equations of the First Kind via Wasserstein Gradient Flows

Solving Fredholm equations of the first kind is crucial in many areas of...

Please sign up or login with your details

Forgot password? Click here to reset