Continuous time limit of the stochastic ensemble Kalman inversion: Strong convergence analysis

The Ensemble Kalman inversion (EKI) method is a method for the estimation of unknown parameters in the context of (Bayesian) inverse problems. The method approximates the underlying measure by an ensemble of particles and iteratively applies the ensemble Kalman update to evolve (the approximation of the) prior into the posterior measure. For the convergence analysis of the EKI it is common practice to derive a continuous version, replacing the iteration with a stochastic differential equation. In this paper we validate this approach by showing that the stochastic EKI iteration converges to paths of the continuous-time stochastic differential equation by considering both the nonlinear and linear setting, and we prove convergence in probability for the former, and convergence in moments for the latter. The methods employed can also be applied to the analysis of more general numerical schemes for stochastic differential equations in general.

[1]  Otmar Scherzer,et al.  On convergence rates of adaptive ensemble Kalman inversion for linear ill-posed problems , 2021, Numerische Mathematik.

[2]  R. Khasminskii.  Stochastic Stability of Differential Equations , 1980 .

[3]  Claudia Schillings,et al.  Well Posedness and Convergence Analysis of the Ensemble Kalman Inversion , 2018 .

[4]  R. Tempone,et al.  Multilevel ensemble Kalman filtering for spatially extended models , 2016, 1608.08558.

[5]  Sebastian Reich,et al.  A mollified ensemble Kalman filter , 2010, 1002.3091.

[6]  Xin T. Tong,et al.  Nonlinear stability and ergodicity of ensemble based Kalman filters , 2015, 1507.08307.

[7]  Haakon Hoel,et al.  Multilevel Ensemble Kalman Filtering based on a sample average of independent EnKF estimators , 2019 .

[8]  Hamidou Tembine,et al.  Deterministic Mean-Field Ensemble Kalman Filtering , 2014, SIAM J. Sci. Comput..

[9]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[10]  Nikolas Nüsken,et al.  Affine invariant interacting Langevin dynamics for Bayesian inference , 2020, SIAM J. Appl. Dyn. Syst..

[11]  Andrew Stuart,et al.  Convergence analysis of ensemble Kalman inversion: the linear, noisy case , 2017, 1702.07894.

[12]  Marco A. Iglesias,et al.  Iterative regularization for ensemble data assimilation in reservoir models , 2014, Computational Geosciences.

[13]  Andrew M. Stuart,et al.  Strong Convergence of Euler-Type Methods for Nonlinear Stochastic Differential Equations , 2002, SIAM J. Numer. Anal..

[14]  Wilhelm Stannat,et al.  Long-Time Stability and Accuracy of the Ensemble Kalman-Bucy Filter for Fully Observed Processes and Small Measurement Noise , 2016, SIAM J. Appl. Dyn. Syst..

[15]  W. Stannat,et al.  Mean field limit of Ensemble Square Root filters - discrete and continuous time , 2020, Foundations of Data Science.

[16]  P. Kloeden,et al.  Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients , 2010, 1010.3756.

[17]  Michael Herty,et al.  A Stabilization of a Continuous Limit of the Ensemble Kalman Filter , 2020, ArXiv.

[18]  Qin Li,et al.  Ensemble Kalman Inversion for nonlinear problems: weights, consistency, and variance bounds , 2020, ArXiv.

[19]  Theresa Lange,et al.  On the continuous time limit of the ensemble Kalman filter , 2019, Math. Comput..

[20]  Andrew M. Stuart,et al.  Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler , 2019, SIAM J. Appl. Dyn. Syst..

[21]  Andrew M. Stuart,et al.  Tikhonov Regularization within Ensemble Kalman Inversion , 2019, SIAM J. Numer. Anal..

[22]  Qin Li,et al.  Ensemble Kalman inversion: mean-field limit and convergence analysis , 2019, Statistics and Computing.

[23]  F. Gland,et al.  Large sample asymptotics for the ensemble Kalman filter , 2009 .

[24]  Marco A. Iglesias,et al.  A regularizing iterative ensemble Kalman method for PDE-constrained inverse problems , 2015, 1505.03876.

[25]  G. Evensen.  Sequential data assimilation with a nonlinear quasi‐geostrophic model using Monte Carlo methods to forecast error statistics , 1994 .

[26]  Geir Evensen,et al.  The Ensemble Kalman Filter: theoretical formulation and practical implementation , 2003 .

[27]  P. Kloeden,et al.  Strong and weak divergence in finite time of Euler's method for stochastic differential equations with non-globally Lipschitz continuous coefficients , 2009, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[28]  Andrew J. Majda,et al.  Performance of Ensemble Kalman Filters in Large Dimensions , 2016, 1606.09321.

[29]  V. Morozov.  On the solution of functional equations by the method of regularization , 1966 .

[30]  D. Oliver,et al.  Ensemble Randomized Maximum Likelihood Method as an Iterative Ensemble Smoother , 2011, Mathematical Geosciences.

[31]  A. Chambolle,et al.  An introduction to Total Variation for Image Analysis , 2009 .

[32]  A. Stuart,et al.  Well-posedness and accuracy of the ensemble Kalman filter in discrete and continuous time , 2013, 1310.3167.

[33]  Pierre Del Moral,et al.  On the stability and the uniform propagation of chaos properties of Ensemble Kalman-Bucy filters , 2016, 1605.09329.

[34]  Theresa Lange,et al.  On the continuous time limit of ensemble square root filters , 2021, Communications in Mathematical Sciences.

[35]  Dirk Blömker,et al.  A Strongly Convergent Numerical Scheme from Ensemble Kalman Inversion , 2017, SIAM J. Numer. Anal..

[36]  A. Stuart,et al.  Ensemble Kalman methods for inverse problems , 2012, 1209.2736.

[37]  Claudia Schillings,et al.  On the Incorporation of Box-Constraints for Ensemble Kalman Inversion , 2019, Foundations of Data Science.

[38]  Sebastian Reich,et al.  Fokker-Planck particle systems for Bayesian inference: Computational approaches , 2019, SIAM/ASA J. Uncertain. Quantification.

[39]  Martin Burger,et al.  Modern regularization methods for inverse problems , 2018, Acta Numerica.

[40]  Andrew M. Stuart,et al.  Ensemble Kalman inversion: a derivative-free technique for machine learning tasks , 2018, Inverse Problems.

[41]  Neil K. Chada,et al.  Multilevel Ensemble Kalman-Bucy Filters , 2020, SIAM/ASA J. Uncertain. Quantification.

[42]  S. Reich.  A dynamical systems framework for intermittent data assimilation , 2011 .

[43]  Kody J. H. Law,et al.  Multilevel ensemble Kalman filtering , 2015, SIAM J. Numer. Anal..

[44]  Jan Mandel,et al.  Convergence of the Square Root Ensemble Kalman Filter in the Large Ensemble Limit , 2014, SIAM/ASA J. Uncertain. Quantification.

[45]  S. Reich,et al.  A localization technique for ensemble Kalman filters , 2009, 0909.1678.

[47]  H. Engl,et al.  Convergence rates for Tikhonov regularisation of non-linear ill-posed problems , 1989 .

[48]  Albert C. Reynolds,et al.  Ensemble smoother with multiple data assimilation , 2013, Comput. Geosci..

[49]  Yuchen Yang,et al.  Adaptive regularisation for ensemble Kalman inversion , 2020 .

[50]  Andrew M. Stuart,et al.  Analysis of the Ensemble Kalman Filter for Inverse Problems , 2016, SIAM J. Numer. Anal..

[51]  Oliver G. Ernst,et al.  Analysis of the Ensemble and Polynomial Chaos Kalman Filters in Bayesian Inverse Problems , 2015, SIAM/ASA J. Uncertain. Quantification.

[52]  Michael Herty,et al.  Kinetic methods for inverse problems , 2018, Kinetic & Related Models.

[53]  M. Hutzenthaler,et al.  Numerical Approximations of Stochastic Differential Equations With Non-globally Lipschitz Continuous Coefficients , 2012, 1203.5809.