Multi-Fidelity Particle Flow Filters based on Log Homotopy
Abstract
This work proposes a new Multi-Fidelity Particle Flow Filter (MFPFF) based on a linear control variate framework and multilevel Monte Carlo methods. Conventional particle filters often suffer from weight collapse and particle degeneracy in high-dimensional spaces. Particle flow filters address this by smoothly transporting prior particles toward the posterior distribution, thereby avoiding the need for resampling. This work constructs multi-fidelity particle flow filters by augmenting a small number of expensive high-fidelity particles (full-order model runs) with a large number of inexpensive low-resolution particles (reduced-order surrogates constructed via intrusive Galerkin projection). These surrogates act as control variates to enhance the statistical estimate of the full-order posterior, yielding enhanced analysis accuracy at comparable computational cost. The work focuses on two particle flows based on log homotopy, the stochastic Gromov flow and deterministic Exact flow. Numerical experiments with the Korteweg-De Vries (KdV) and Quasi-Geostrophic (QG) test problems demonstrate that the proposed MFPFF achieves accuracy comparable to high-fidelity simulations while significantly reducing computational expense.
Related
- An Analytical Framework for a Multi-Particle Oja Flow
- Learning to Bias: Machine Learning-Enhanced Particle Filters
- From POMDP Theory to Deep RL with Particle Filters
- On the Oja-Flow-Based Low-Rank Approximation of Kalman-Bucy Filters for Linear Time-Varying Systems
- Improving Ensemble Filters with Flow Matching
BibTeX
@misc{bhattacharjee2026multifidelity,
title = {{Multi-Fidelity Particle Flow Filters based on Log Homotopy}},
author = {Abhinab Bhattacharjee and Andrey A. Popov and Amit N. Subrahmanya and Adrian Sandu},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.35712},
eprint = {2610.35712},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.35712},
}
RIS
TY - UNPB
TI - Multi-Fidelity Particle Flow Filters based on Log Homotopy
AU - Abhinab Bhattacharjee
AU - Andrey A. Popov
AU - Amit N. Subrahmanya
AU - Adrian Sandu
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.35712
UR - https://arxiv.org/abs/2610.35712
AB - This work proposes a new Multi-Fidelity Particle Flow Filter (MFPFF) based on a linear control variate framework and multilevel Monte Carlo methods. Conventional particle filters often suffer from weight collapse and particle degeneracy in high-dimensional spaces. Particle flow filters address this by smoothly transporting prior particles toward the posterior distribution, thereby avoiding the need for resampling. This work constructs multi-fidelity particle flow filters by augmenting a small number of expensive high-fidelity particles (full-order model runs) with a large number of inexpensive low-resolution particles (reduced-order surrogates constructed via intrusive Galerkin projection). These surrogates act as control variates to enhance the statistical estimate of the full-order posterior, yielding enhanced analysis accuracy at comparable computational cost. The work focuses on two particle flows based on log homotopy, the stochastic Gromov flow and deterministic Exact flow. Numerical experiments with the Korteweg-De Vries (KdV) and Quasi-Geostrophic (QG) test problems demonstrate that the proposed MFPFF achieves accuracy comparable to high-fidelity simulations while significantly reducing computational expense.
ER -