Ensemble Kalman inversion: mean-field limit and convergence analysis
From MaRDI portal
Publication:2029092
DOI10.1007/S11222-020-09976-0zbMATH Open1462.62023OpenAlexW3121011245MaRDI QIDQ2029092FDOQ2029092
Abstract: Ensemble Kalman Inversion (EKI) has been a very popular algorithm used in Bayesian inverse problems. It samples particles from a prior distribution, and introduces a motion to move the particles around in pseudo-time. As the pseudo-time goes to infinity, the method finds the minimizer of the objective function, and when the pseudo-time stops at , the ensemble distribution of the particles resembles, in some sense, the posterior distribution in the linear setting. The ideas trace back further to Ensemble Kalman Filter and the associated analysis, but to today, when viewed as a sampling method, why EKI works, and in what sense with what rate the method converges is still largely unknown. In this paper, we analyze the continuous version of EKI, a coupled SDE system, and prove the mean field limit of this SDE system. In particular, we will show that 1. as the number of particles goes to infinity, the empirical measure of particles following SDE converges to the solution to a Fokker-Planck equation in Wasserstein 2-distance with an optimal rate, for both linear and weakly nonlinear case; 2. the solution to the Fokker-Planck equation reconstructs the target distribution in finite time in the linear case.
Recommendations
- Continuous Time Limit of the Stochastic Ensemble Kalman Inversion: Strong Convergence Analysis
- Complete Deterministic Dynamics and Spectral Decomposition of the Linear Ensemble Kalman Inversion
- Convergence acceleration of ensemble Kalman inversion in nonlinear settings
- Ensemble Kalman sampler: mean-field limit and convergence analysis
- Gradient flow structure and convergence analysis of the ensemble Kalman inversion for nonlinear forward models
Cites work
- scientific article; zbMATH DE number 1666084 (Why is no real title available?)
- scientific article; zbMATH DE number 3889112 (Why is no real title available?)
- scientific article; zbMATH DE number 4211245 (Why is no real title available?)
- scientific article; zbMATH DE number 2106098 (Why is no real title available?)
- scientific article; zbMATH DE number 2117879 (Why is no real title available?)
- A dynamical systems framework for intermittent data assimilation
- A strongly convergent numerical scheme from ensemble Kalman inversion
- A well-posedness theory in measures for some kinetic models of collective motion
- Analysis of the ensemble Kalman filter for inverse problems
- Analysis of the ensemble and polynomial chaos Kalman filters in Bayesian inverse problems
- Convergence analysis of ensemble Kalman inversion: the linear, noisy case
- Data Assimilation
- Data assimilation: the Schrödinger perspective
- Deterministic mean-field ensemble Kalman filtering
- Ensemble Kalman methods for inverse problems
- Interacting Langevin diffusions: gradient structure and ensemble Kalman sampler
- Inverse problems: a Bayesian perspective
- Kinetic methods for inverse problems
- Large sample asymptotics for the ensemble Kalman filter
- On the continuous time limit of the ensemble Kalman filter
- On the rate of convergence in Wasserstein distance of the empirical measure
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- Stochastic mean-field limit: non-Lipschitz forces and swarming
- Well posedness and convergence analysis of the ensemble Kalman inversion
Cited in
(28)- Continuous Time Limit of the Stochastic Ensemble Kalman Inversion: Strong Convergence Analysis
- Convergence analysis of ensemble Kalman inversion: the linear, noisy case
- Ensemble Kalman inversion for nonlinear problems: weights, consistency, and variance bounds
- Recent trends on nonlinear filtering for inverse problems
- Filtering Methods for Coupled Inverse Problems
- A stabilization of a continuous limit of the ensemble Kalman inversion
- Propagation of chaos: a review of models, methods and applications. II: Applications
- Neural dynamical operator: continuous spatial-temporal model with gradient-based and derivative-free optimization methods
- Rough McKean-Vlasov dynamics for robust ensemble Kalman filtering
- Markov chain generative adversarial neural networks for solving Bayesian inverse problems in physics applications
- Interacting Langevin diffusions: gradient structure and ensemble Kalman sampler
- Parameterizations for ensemble Kalman inversion
- Complete Deterministic Dynamics and Spectral Decomposition of the Linear Ensemble Kalman Inversion
- Adaptive Tikhonov strategies for stochastic ensemble Kalman inversion
- Less interaction with forward models in Langevin dynamics: enrichment and homotopy
- The mean-field ensemble Kalman filter: near-Gaussian setting
- Sharp propagation of chaos for the ensemble Langevin sampler
- Adaptive Ensemble Kalman Inversion with Statistical Linearization
- Constrained ensemble Langevin Monte Carlo
- Subsampling in ensemble Kalman inversion
- On convergence rates of adaptive ensemble Kalman inversion for linear ill-posed problems
- Gradient flow structure and convergence analysis of the ensemble Kalman inversion for nonlinear forward models
- Convergence acceleration of ensemble Kalman inversion in nonlinear settings
- EnKSGD: a class of preconditioned black box optimization and inversion algorithms
- Iterated Kalman methodology for inverse problems
- Localized ensemble Kalman inversion
- On the ensemble Kalman inversion under inequality constraints
- Ensemble Kalman sampler: mean-field limit and convergence analysis
This page was built for publication: Ensemble Kalman inversion: mean-field limit and convergence analysis
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2029092)
