Poster
A Finite-Particle Convergence Rate for Stein Variational Gradient Descent
Jiaxin Shi · Lester Mackey
Great Hall & Hall B1+B2 (level 1) #1126
Abstract:
We provide the first finite-particle convergence rate for Stein variational gradient descent (SVGD), a popular algorithm for approximating a probability distribution with a collection of particles. Specifically, whenever the target distribution is sub-Gaussian with a Lipschitz score, SVGD with particles and an appropriate step size sequence drives the kernel Stein discrepancy to zero at an order rate. We suspect that the dependence on can be improved, and we hope that our explicit, non-asymptotic proof strategy will serve as a template for future refinements.
Chat is not available.