Pith. sign in

Interacting Langevin Diffusions: Gradient Structure And Ensemble Kalman Sampler

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Solving inverse problems without the use of derivatives or adjoints of the forward model is highly desirable in many applications arising in science and engineering. In this paper, we propose a new version of such a methodology, a framework for its analysis, and numerical evidence of the practicality of the method proposed. Our starting point is an ensemble of over-damped Langevin diffusions which interact through a single preconditioner computed as the empirical ensemble covariance. We demonstrate that the nonlinear Fokker-Planck equation arising from the mean-field limit of the associated stochastic differential equation (SDE) has a novel gradient flow structure, built on the Wasserstein metric and the covariance matrix of the noisy flow. Using this structure, we investigate large time properties of the Fokker-Planck equation, showing that its invariant measure coincides with that of a single Langevin diffusion, and demonstrating exponential convergence to the invariant measure in a number of settings. We introduce a new noisy variant on ensemble Kalman inversion (EKI) algorithms found from the original SDE by replacing exact gradients with ensemble differences; this defines the ensemble Kalman sampler (EKS). Numerical results are presented which demonstrate its efficacy as a derivative-free approximate sampler for the Bayesian posterior arising from inverse problems.

citation-role summary

background 1

citation-polarity summary

fields

math.OC 1

years

2019 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Accelerated Information Gradient flow

math.OC · 2019-09-04 · conditional · novelty 6.0

The authors derive and analyze accelerated Nesterov-type gradient flows in probability space under four information metrics and use them to build faster mean-field MCMC sampling algorithms.

citing papers explorer

Showing 1 of 1 citing paper.

  • Accelerated Information Gradient flow math.OC · 2019-09-04 · conditional · none · ref 10 · internal anchor

    The authors derive and analyze accelerated Nesterov-type gradient flows in probability space under four information metrics and use them to build faster mean-field MCMC sampling algorithms.