Parameterized Wasserstein Hamiltonian Flow

TL;DR

This paper introduces a deterministic, neural network-based numerical method for computing Wasserstein Hamiltonian flows that preserves energy and scales efficiently to high dimensions without requiring neural network training.

Contribution

It develops a novel parameterized ODE approach using neural networks and symplectic integrators to solve Wasserstein Hamiltonian flows without stochastic training.

Findings

Preserves total energy during computation.

Scales effectively to high-dimensional problems.

Avoids stochastic gradient descent errors.

Abstract

In this work, we propose a numerical method to compute the Wasserstein Hamiltonian flow (WHF), which is a Hamiltonian system on the probability density manifold. Many well-known PDE systems can be reformulated as WHFs. We use parameterized function as push-forward map to characterize the solution of WHF, and convert the PDE to a finite-dimensional ODE system, which is a Hamiltonian system in the phase space of the parameter manifold. We establish error analysis results for the continuous time approximation scheme in Wasserstein metric. For the numerical implementation, we use neural networks as push-forward maps. We apply an effective symplectic scheme to solve the derived Hamiltonian ODE system so that the method preserves some important quantities such as total energy. The computation is done by fully deterministic symplectic integrator without any neural network training. Thus, our method does not involve direct optimization over network parameters and hence can avoid the error introduced by stochastic gradient descent (SGD) methods, which is usually hard to quantify and measure. The proposed algorithm is a sampling-based approach that scales well to higher dimensional problems. In addition, the method also provides an alternative connection between the Lagrangian and Eulerian perspectives of the original WHF through the parameterized ODE dynamics.