On Sequential Entropic Optimal Transport Filter and its Multilevel Variants
Abstract
We consider the problem of filtering partially observed diffusions associated to discrete time observations. This problem requires the development of advanced numerical methods such as particle filters. In this article we develop a new sequential entropic optimal transport filter (EOTF). The main idea is to sample from successive couplings of the filters. To achieve this, we adopt the approach of an entropic optimal transport (EOT) update implemented through a learned Schrödinger potential, in the spirit of the light Schrödinger bridge methodology \cite{korotin2024light}. Based on this, we develop a multilevel version of this filter (ML-EOTF) in which consecutive discretization levels are coupled at the terminal time by a scaled EOT plan with level-dependent regularization epsl=eps0 hlκ with discretization stepsize hl. Under mild conditions, we show that the level-difference estimator with exact Schrödinger potentials has variance of order Nl−1{hlβ+epsl}, where β is the strong-error for the discretized SDE. The analysis is then extended to learned potentials, with all approximation and optimization errors summarized by a joint Kullback--Leibler discrepancy whose contribution to the mean squared error is explicitly quantified. Combined with a fixed-time weak-error estimate, this yields the canonical multilevel complexity cO(δ−2|logδ|2) to achieve an MSE of δ2 for Euler--Maruyama discretizations. Numerical experiments validate the results.
Related
- Sequential Entropic Optimal Transport for Bayesian Inverse Problems via Multilevel Monte Carlo
- First-order Γ-expansion for entropic optimal transport with non-degenerate costs
- On the Linear Convergence of SISTA for Entropic Martingale Optimal Transport
- Low-Budget Active Learning through Entropic Optimal Transport
- Projected McKean--Vlasov Dynamics for Entropic Weak Optimal Transport
BibTeX
@misc{zhao2026sequential,
title = {{On Sequential Entropic Optimal Transport Filter and its Multilevel Variants}},
author = {Ke Zhao and Ajay Jasra},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01752},
eprint = {2611.01752},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01752},
}
RIS
TY - UNPB
TI - On Sequential Entropic Optimal Transport Filter and its Multilevel Variants
AU - Ke Zhao
AU - Ajay Jasra
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01752
UR - https://arxiv.org/abs/2611.01752
AB - We consider the problem of filtering partially observed diffusions associated to discrete time observations. This problem requires the development of advanced numerical methods such as particle filters. In this article we develop a new sequential entropic optimal transport filter (EOTF). The main idea is to sample from successive couplings of the filters. To achieve this, we adopt the approach of an entropic optimal transport (EOT) update implemented through a learned Schrödinger potential, in the spirit of the light Schrödinger bridge methodology \cite{korotin2024light}. Based on this, we develop a multilevel version of this filter (ML-EOTF) in which consecutive discretization levels are coupled at the terminal time by a scaled EOT plan with level-dependent regularization eps_l=eps_0 h_l^κ with discretization stepsize h_l. Under mild conditions, we show that the level-difference estimator with exact Schrödinger potentials has variance of order N_l^−1{h_l^β+eps_l}, where β is the strong-error for the discretized SDE. The analysis is then extended to learned potentials, with all approximation and optimization errors summarized by a joint Kullback--Leibler discrepancy whose contribution to the mean squared error is explicitly quantified. Combined with a fixed-time weak-error estimate, this yields the canonical multilevel complexity cO(δ^−2|logδ|^2) to achieve an MSE of δ^2 for Euler--Maruyama discretizations. Numerical experiments validate the results.
ER -