Wasserstein gradient flows provide a powerful means of understanding and solving many diffusion equations. Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gradient descent over entropy functionals in Wasserstein space. This equivalence, introduced by Jordan, Kinderlehrer and Otto, inspired the so-called JKO scheme to approximate these diffusion processes via an implicit discretization of the gradient flow in Wasserstein space. Solving the optimization problem associated with each JKO step, however, presents serious computational challenges. We introduce a scalable method to approximate Wasserstein gradient flows, targeted to machine learning applications. Our approach relies on input-convex neural networks (ICNNs) to discretize the JKO steps, which can be optimized by stochastic gradient descent. Contrarily to previous work, our method does not require domain discretization or particle simulation. As a result, we can sample from the measure at each time step of the diffusion and compute its probability density. We demonstrate the performance of our algorithm by computing diffusions following the Fokker-Planck equation and apply it to unnormalized density sampling as well as nonlinear filtering.

This paper develops the first theoretical analysis on SVGD.

This paper deals with the problem of efficient sampling from a stochastic differential equation, given the drift function and the diffusion matrix.

Jacobian trace), or generalizations involving higher-order derivatives.

The theoretical contributions of our work and the works [Mguni et al., AAAI'18; Mguni et al., AAMAS'19] mentioned

Notice that we did not need to use the common identity (ρ f) = ρ f + ( ρ) f, nor expand with log π = H .

Approximate Bayesian inference estimates descriptors of an intractable target distribution - in essence, an optimization problem within a family of distributions.

This paper deals with the problem of efficient sampling from a stochastic differential equation, given the drift function and the diffusion matrix.