Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 50 min ago
PreprintarXiv licencearXiv

A perturbation theory for Feynman-Kac models and their particle interpretations

Abstract

We develop a perturbation analysis of Feynman--Kac models, describing how local errors introduced at each step of the Feynman--Kac recursion propagate over time. Under general conditions on the potential functions and the Markov transitions, which are shown to hold for a large class of state-space models, we prove that the global error for any time horizon T≥ 1 is bounded by C ΔTlog(1+ΔT−1), where ΔT is the largest local error; this bound holds both for the prediction and the updated models. These conditions require no Lyapunov function and no stability of the Markov transitions, and allow for non-compact state spaces: confinement is provided by the potential functions. Our perturbation bounds hold in total variation and in the Kolmogorov norm; for the latter, we extend the Hardy--Krause variation and the Koksma--Hlawka inequality to unbounded domains. Our perturbation theory is applied to derive time-uniform bounds for linearized Kalman filters, Euler schemes for partially observed diffusions and nudged state-space models, as well as high-probability error bounds, uniform over whole trajectories, for particle filters and, more generally, for mean field particle methods such as sequential Monte Carlo and diffusion Monte Carlo algorithms.

Related

  1. Smooth perturbation theory and generic Cantor spectrum for multi-dimensional monotone quasiperiodic operators
    Ilya Kachkovskiy, Leonid Parnovski, Roman Shterenberg
    arXivPreprintarXiv licenceFull textAnalysis & PDEsMathematical physicsarXiv
  2. An Accurate Zeroth-Order Perturbation Theory for Solving Power-Law Potentials within the Framework of the Asymptotic Iteration Method
    A. J. Sous, Ibsal Assi, Nasser Saad
    arXivPreprintCC0Full textMathematical physicsarXiv
  3. Convex-Gaussianity of fermionic Gibbs states in perturbation theory
    Kaifeng Bu, Yuanjie Ren
    arXivPreprintarXiv licenceFull textMathematical physicsCondensed matterarXiv
  4. Perturbation Theory for Time-Dependent Point Interactions with Discrete Spectrum
    Kaya Güven Akbaş, Fatih Erman, O. Teoman Turgut
    arXivPreprintarXiv licenceFull textMathematical physicsQuantum physics & quantum informationarXiv
  5. From POMDP Theory to Deep RL with Particle Filters
    Kevin Tan, Ziping Xu
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
BibTeX
@misc{moral2026perturbation,
  title = {{A perturbation theory for Feynman-Kac models and their particle interpretations}},
  author = {Pierre Del Moral and Mathieu Gerber},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.21587},
  eprint = {2610.21587},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.21587},
}
RIS
TY  - UNPB
TI  - A perturbation theory for Feynman-Kac models and their particle interpretations
AU  - Pierre Del Moral
AU  - Mathieu Gerber
PY  - 2026
DA  - 2026/10/15
PB  - arXiv
DO  - 10.48550/arxiv.2610.21587
UR  - https://arxiv.org/abs/2610.21587
AB  - We develop a perturbation analysis of Feynman--Kac models, describing how local errors introduced at each step of the Feynman--Kac recursion propagate over time. Under general conditions on the potential functions and the Markov transitions, which are shown to hold for a large class of state-space models, we prove that the global error for any time horizon T≥ 1 is bounded by C Δ_Tlog(1+Δ_T^−1), where Δ_T is the largest local error; this bound holds both for the prediction and the updated models. These conditions require no Lyapunov function and no stability of the Markov transitions, and allow for non-compact state spaces: confinement is provided by the potential functions. Our perturbation bounds hold in total variation and in the Kolmogorov norm; for the latter, we extend the Hardy--Krause variation and the Koksma--Hlawka inequality to unbounded domains. Our perturbation theory is applied to derive time-uniform bounds for linearized Kalman filters, Euler schemes for partially observed diffusions and nudged state-space models, as well as high-probability error bounds, uniform over whole trajectories, for particle filters and, more generally, for mean field particle methods such as sequential Monte Carlo and diffusion Monte Carlo algorithms.
ER  -