Approximate inference with Wasserstein gradient flows

Abstract

We present a novel approximate inference method for diffusion processes, based on the Wasserstein gradient flow formulation of the diffusion. In this formulation, the time-dependent density of the diffusion is derived as the limit of implicit Euler steps that follow the gradients of a particular free energy functional. Existing methods for computing Wasserstein gradient flows rely on discretization of the domain of the diffusion, prohibiting their application to domains in more than several dimensions. We propose instead a discretization-free inference method that computes the Wasserstein gradient flow directly in a space of continuous functions. We characterize approximation properties of the proposed method and evaluate it on a nonlinear filtering task, finding performance comparable to the state-of-the-art for filtering diffusions.

References in corpus (4)

• Exact simulation of diffusions
• Stochastic Optimization for Large-scale Optimal Transport
• Gaussian filtering and variational approximations for Bayesian smoothing in continuous-discrete stochastic dynamic systems
• A variational approach to path estimation and parameter inference of hidden diffusion processes

Cited by in corpus (10)

• Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimation
• Statistical Inference for Generative Models with Maximum Mean Discrepancy
• Particle-based Energetic Variational Inference
• Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks
• Sqrt(d) Dimension Dependence of Langevin Monte Carlo
• Hessian-Free High-Resolution Nesterov Acceleration for Sampling
• Accelerated Flow for Probability Distributions
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization
• The Wasserstein Proximal Gradient Algorithm
• Dynamic Flows on Curved Space Generated by Labeled Data