Birth-death dynamics for sampling: Global convergence, approximations and their asymptotics

11/01/2022
by   Yulong Lu, et al.
0

Motivated by the challenge of sampling Gibbs measures with nonconvex potentials, we study a continuum birth-death dynamics. We prove that the probability density of the birth-death governed by Kullback-Leibler divergence or by χ^2 divergence converge exponentially fast to the Gibbs equilibrium measure with a universal rate that is independent of the potential barrier. To build a practical numerical sampler based on the pure birth-death dynamics, we consider an interacting particle system which relies on kernel-based approximations of the measure and retains the gradient-flow structure. We show on the torus that the kernelized dynamics Γ-converges, on finite time intervals, to the pure birth-death dynamics as the kernel bandwidth shrinks to zero. Moreover we provide quantitative estimates on the bias of minimizers of the energy corresponding to the kernalized dynamics. Finally we prove the long-time asymptotic results on the convergence of the asymptotic states of the kernalized dynamics towards the Gibbs measure.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/09/2022

Second Order Ensemble Langevin Method for Sampling and Inverse Problems

We propose a sampling method based on an ensemble approximation of secon...
research
06/23/2023

On a Class of Gibbs Sampling over Networks

We consider the sampling problem from a composite distribution whose pot...
research
05/27/2021

Sampling from the Gibbs Distribution in Congestion Games

Logit dynamics is a form of randomized game dynamics where players have ...
research
02/25/2022

A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling

As a counterpoint to classical stochastic particle methods for linear di...
research
10/24/2022

Sampling with Mollified Interaction Energy Descent

Sampling from a target measure whose density is only known up to a norma...
research
10/29/2020

Rates of convergence for Gibbs sampling in the analysis of almost exchangeable data

Motivated by de Finetti's representation theorem for partially exchangea...
research
08/25/2019

Hypocoercivity properties of adaptive Langevin dynamics

Adaptive Langevin dynamics is a method for sampling the Boltzmann-Gibbs ...

Please sign up or login with your details

Forgot password? Click here to reset