4 papers
Stein Variational Gradient Descent dynamics for highly concentrated kernels
José A. Carrillo, Jakub Skrzeczkowski, Jethro Warnett
Stein Variational Gradient Descent (SVGD) is a widely used in practice algorithm for scalable sampling with deterministic particle updates. We study its behavior in the singular li…
A new formula for the Wasserstein distance between solutions to (nonlinear) continuity equations
José A. Carrillo, Piotr Gwiazda, Jakub Skrzeczkowski
Given two continuity equations with density-dependent velocities, we provide a new formula for the Wasserstein distance between the solutions in terms of the difference of velociti…
Rate of Convergence for a Nonlocal-to-local Limit in One Dimension
José A. Carrillo, Charles Elbar, Stefano Fronzoni +1
We consider a nonlocal approximation of the quadratic porous medium equation where the pressure is given by a convolution with a mollification kernel. It is known that when the ker…
The Stein-log-Sobolev inequality and the exponential rate of convergence for the continuous Stein variational gradient descent method
José A. Carrillo, Jakub Skrzeczkowski, Jethro Warnett
The Stein Variational Gradient Descent method is a variational inference method in statistics that has recently received a lot of attention. The method provides a deterministic app…