Learning Discriminators for Resampling in the Ensemble Gaussian Mixture Filter through a Normalizing Flow Approach

• URL: http://arxiv.org/abs/2605.01089v1
• Date: Fri, 01 May 2026 20:47:38 GMT
• Title: Learning Discriminators for Resampling in the Ensemble Gaussian Mixture Filter through a Normalizing Flow Approach
• Abstract summary: This work introduces the discriminator-informed resampling procedure, that augments the posterior resampling step with a discriminator that accepts or rejects candidate particles based on their physical plausibility.<n> Numerical experiments on both the Ikeda map and the Lorenz '63 system show that discriminator informed resampling procedure consistently reduces error relative to the standard EnGMF in low-ensemble regimes.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ensemble Gaussian mixture filter (EnGMF) is a powerful, convergent particle filter capable of medium-to-high dimensional non-linear filtering. The EnGMF relies on a resampling step that can generate physically unrealistic posterior samples, that would subsequently produce physically meaningless forecasts. This work introduces the discriminator-informed resampling procedure, that augments the posterior resampling step with a discriminator that accepts or rejects candidate particles based on their physical plausibility. In this work these discriminators are learned through a normalizing flow approach. Numerical experiments on both the Ikeda map and the Lorenz '63 system show that discriminator informed resampling procedure consistently reduces error relative to the standard EnGMF in low-ensemble regimes.

Related papers

• An adaptive split-combine Gaussian mixture filter for nonlinear and multimodal state estimation [3.796192753421465]
  We develop an adaptive split-combine Gaussian mixture filter (AMF) that estimates the time evolution of asymmetric and multimodal PDFs.<n>AMF consistently outperforms various baseline filters across diverse benchmarks.<n>We also propose a parallel implementation of AMF, allowing high-fidelity PDF estimation with practical computational cost.
  arXiv  Detail & Related papers  (2026-08-05T04:21:22Z)
• Deformable Wiener Filter for Future Video Coding [55.405068056883614]
  We propose a deformable Wiener Filter (DWF) for in-loop filters in Versatile Video Coding (VVC)<n>It combines the local and non-local characteristics and supervisedly trains the filter coefficients based on the Wiener Filter theory.<n>It achieves 1.16%, 1.92%, and 2.67% bit-rate savings on average compared to the VTM-11.0 for All Intra, Random Access, and Low-Delay B configurations.
  arXiv  Detail & Related papers  (2026-06-01T02:24:07Z)
• Filtered Markovian Projection: Dimensionality Reduction in Filtering for Stochastic Reaction Networks [0.9599644507730105]
  A typical challenge in practical problems modeled by reaction networks (SRNs) is that only a few state variables can be dynamically observed.<n>We propose to use a dimensionality reduction technique based on the Markovian projection (MP), initially introduced for forward problems.<n>The novel method employs a reduced-variance particle filter for estimating the jump intensities of the projected model and solves the filtering equations in a low-dimensional space.
  arXiv  Detail & Related papers  (2025-02-11T19:45:40Z)
• Deep MMD Gradient Flow without adversarial training [69.76417786943217]
  We propose a gradient flow procedure for generative modeling by transporting particles from an initial source distribution to a target distribution. The noise-adaptive Wasserstein Gradient of the Maximum Mean Discrepancy (MMD) is trained on data distributions corrupted by increasing levels of noise. We demonstrate the validity of the approach when MMD is replaced by a lower bound on the KL divergence.
  arXiv  Detail & Related papers  (2024-05-10T19:10:45Z)
• Normalizing Flow-based Differentiable Particle Filters [16.164656853940464]
  We present a differentiable particle filtering framework that usesconditional normalizing flows to build its dynamic model, proposal distribution, and measurement model.<n>We derive the theoretical properties of the proposed filters and evaluate the proposed normalizing flow-based differentiable particle filters' performance through a series of numerical experiments.
  arXiv  Detail & Related papers  (2024-03-03T12:23:17Z)
• Closed-form Filtering for Non-linear Systems [83.91296397912218]
  We propose a new class of filters based on Gaussian PSD Models, which offer several advantages in terms of density approximation and computational efficiency. We show that filtering can be efficiently performed in closed form when transitions and observations are Gaussian PSD Models. Our proposed estimator enjoys strong theoretical guarantees, with estimation error that depends on the quality of the approximation and is adaptive to the regularity of the transition probabilities.
  arXiv  Detail & Related papers  (2024-02-15T08:51:49Z)
• Nonlinear Filtering with Brenier Optimal Transport Maps [6.048942663334447]
  This paper is concerned with the problem of nonlinear filtering, i.e., computing the conditional distribution of the state of a dynamical system.<n>Conventional sequential importance resampling (SIR) particle filters suffer from fundamental limitations, in scenarios involving degenerate likelihoods or high-dimensional states.<n>In this paper, we explore an alternative method, which is based on estimating the Brenier optimal transport (OT) map from the current prior distribution of the state to the posterior distribution at the next time step.
  arXiv  Detail & Related papers  (2023-10-21T01:34:30Z)
• Computational Doob's h-transforms for Online Filtering of Discretely Observed Diffusions [65.74069050283998]
  We propose a computational framework to approximate Doob's $h$-transforms. The proposed approach can be orders of magnitude more efficient than state-of-the-art particle filters.
  arXiv  Detail & Related papers  (2022-06-07T15:03:05Z)
• Deep Learning for the Benes Filter [91.3755431537592]
  We present a new numerical method based on the mesh-free neural network representation of the density of the solution of the Benes model. We discuss the role of nonlinearity in the filtering model equations for the choice of the domain of the neural network.
  arXiv  Detail & Related papers  (2022-03-09T14:08:38Z)
• Innovative And Additive Outlier Robust Kalman Filtering With A Robust Particle Filter [68.8204255655161]
  We propose CE-BASS, a particle mixture Kalman filter which is robust to both innovative and additive outliers, and able to fully capture multi-modality in the distribution of the hidden state. Furthermore, the particle sampling approach re-samples past states, which enables CE-BASS to handle innovative outliers which are not immediately visible in the observations, such as trend changes.
  arXiv  Detail & Related papers  (2020-07-07T07:11:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.