Litcius/Paper detail

Ensemble Kalman Sampler: Mean-field Limit and Convergence Analysis

Zhiyan Ding, Qin Li

2021SIAM Journal on Mathematical Analysis37 citationsDOI

Abstract

The ensemble Kalman sampler (EKS) is a method introduced in [Garbuno-Inigo et al., SIAM J. Appl. Dyn. Syst., 19 (2020), pp. 412--441] to find approximately independent and identically distributed samples from a target distribution. As of today, why the algorithm works and how it converges is mostly unknown. The continuous version of the algorithm is a set of coupled stochastic differential equations (SDEs). In this paper, we prove the well posedness of the SDE system and justify its mean-field limit is a Fokker--Planck equation, whose long time equilibrium is the target distribution. We further demonstrate that the convergence rate is near optimal ($J^{-1/2}$ with $J$ being the number of particles). These results, combined with the in-time convergence of the Fokker--Planck equation to its equilibrium [J. A. Carrillo and U. Vaes, preprint, arXiv:1910.07555, 2019] justify the validity of the EKS, and provide the convergence rate as a sampling method.

Topics & Concepts

MathematicsPreprintStochastic differential equationConvergence (economics)Kalman filterFokker–Planck equationLimit (mathematics)Rate of convergenceApplied mathematicsIndependent and identically distributed random variablesDistribution (mathematics)Field (mathematics)Differential equationMathematical analysisStatisticsRandom variablePhysicsComputer scienceQuantum mechanicsPure mathematicsEconomicsComputer networkChannel (broadcasting)Economic growthMarkov Chains and Monte Carlo MethodsStochastic processes and financial applicationsGaussian Processes and Bayesian Inference