Global Non-convex Optimization With Discretized Diffusions

Authors:
Murat A Erdogdu University of Toronto
Lester Mackey Microsoft Research
Ohad Shamir Weizmann Institute of Science

Introduction:

An Euler discretization of the Langevin diffusion is known to converge to the global minimizers of certain convex and non-convex optimization problems.This allows us to design diffusions suitable for globally optimizing convex and non-convex functions not covered by the existing Langevin theory.

Abstract:

An Euler discretization of the Langevin diffusion is known to converge to the global minimizers of certain convex and non-convex optimization problems. We show that this property holds for any suitably smooth diffusion and that different diffusions are suitable for optimizing different classes of convex and non-convex functions. This allows us to design diffusions suitable for globally optimizing convex and non-convex functions not covered by the existing Langevin theory. Our non-asymptotic analysis delivers computable optimization and integration error bounds based on easily accessed properties of the objective and chosen diffusion. Central to our approach are new explicit Stein factor bounds on the solutions of Poisson equations. We complement these results with improved optimization guarantees for targets other than the standard Gibbs measure.

You may want to know: