Marco Iglesias
  • Home
  • Research
  • Publications
  • CV
  1. Methods
  2. Ensemble Kalman Inversion (EKI)
  • Methods
    • Ensemble Kalman Inversion (EKI)
    • Deep Learning Emulators
    • Bayesian Inversion
    • Iterative Regularisation
    • Level-set Parameterisations
  • Applications
    • Resin Transfer Moulding (RTM)
    • Thermophysical Imaging of Buildings’ Walls
    • Magnetic Resonance Elastography (MRE)
    • Electrical Resistivity Tomography

On this page

  • Initial Work
  • EKI from an Iterative Regularisation Perspective
  • EKI from a Bayesian Perspective.
  1. Methods
  2. Ensemble Kalman Inversion (EKI)

Ensemble Kalman Inversion (EKI)

Initial Work

My work on Ensemble Kalman Inversion (EKI) originated with the paper [1], where concepts from the Ensemble Kalman Filter (EnKF), introduced by Evensen, were reformulated as an iterative solver for PDE-constrained inverse problems. Although similar ensemble ideas had previously been used for parameter identification in oil reservoir modelling, this work provided a unifying inverse problems perspective. As a result, EKI gained broader visibility within the inverse problems community and has since grown into an independent and active research direction.

EKI from an Iterative Regularisation Perspective

The initial work in [1] showed that a straightforward application of the EnKF as an iterative solver can suffer from stability issues similar to those encountered in classical iterative methods for ill-posed inverse problems: although the data misfit may decrease, the reconstruction error can grow. This observation motivated my subsequent work in [2], where ideas from Hanke’s regularising Levenberg–Marquardt method were adapted to modify EKI through the introduction of a regularisation parameter. From a heuristic perspective, this modification can be viewed as motivating EKI as a derivative-free approximation of the Levenberg–Marquardt method, in which ensemble-based covariances play the role of approximating local sensitivity information. The resulting scheme enables smoother updates and provides a principled stopping criterion. Although no theoretical analysis was developed at the time, the numerical results were very encouraging.

EKI from a Bayesian Perspective.

From a Bayesian perspective, EKI can be heuristically motivated using ideas from sequential Monte Carlo methods, where tempering is employed to construct a sequence of intermediate measures bridging the prior and the posterior. Within this viewpoint, EKI may be interpreted as replacing each intermediate posterior by a Gaussian approximation, linearising the forward map, and substituting explicit derivative information with ensemble-based covariance estimates. In the works [3], [4], we adopted this perspective to derive alternative, adaptive choices of the regularisation parameter in EKI, leading to methods that are robust and stable while still achieving fast convergence.

References
[1]
M. A. Iglesias, K. J. H. Law, and A. M. Stuart, “Ensemble kalman methods for inverse problems,” Inverse Problems, vol. 29, no. 4, p. 045001, Mar. 2013, doi: 10.1088/0266-5611/29/4/045001.
[2]
M. A. Iglesias, “A regularizing iterative ensemble Kalman method for PDE-constrained inverse problems,” Inverse Problems, vol. 32, no. 2, p. 025002, 2016, Available: http://stacks.iop.org/0266-5611/32/i=2/a=025002
[3]
M. Iglesias and Y. Yang, “Adaptive regularisation for ensemble kalman inversion,” Inverse Problems, vol. 37, no. 2, p. 025008, Jan. 2021, doi: 10.1088/1361-6420/abd29b.
[4]
M. Iglesias, M. Park, and M. V. Tretyakov, “Bayesian inversion in resin transfer molding,” Inverse Problems, vol. 34, no. 10, p. 105002, Jul. 2018, doi: 10.1088/1361-6420/aad1cc.