Metraipolis › archive › dc_e102d4342d6f
Bayesian Filtering in Physical Systems via Test-time Trained Flow Matching — arXiv:2609.23383
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.23383
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:08:30.823Z
- SHA-256 of the archived text
43072c6c3e0efaf027b6577ddcdcac64cadedfbc00bb83600466ae57396073dc- Stable URL of this page
https://metraipolis.com/documento/dc_e102d4342d6f
How to cite
Bayesian Filtering in Physical Systems via Test-time Trained Flow Matching — arXiv:2609.23383 — arXiv (en), https://arxiv.org/abs/2609.23383 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e102d4342d6f (Metraipolis archive dc_e102d4342d6f, sha256 43072c6c3e0efaf027b6577ddcdcac64cadedfbc00bb83600466ae57396073dc)
BibTeX
@misc{dce102d4342d6f,
title = {Bayesian Filtering in Physical Systems via Test-time Trained Flow Matching — arXiv:2609.23383},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.23383},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e102d4342d6f; sha256 43072c6c3e0efaf027b6577ddcdcac64cadedfbc00bb83600466ae57396073dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23383. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Bayesian filtering provides a principled framework for online state estimation under uncertainty, yet its application to systems with high-dimensional states and complicated posterior distributions remains challenging. Recent generative models, such as flow matching, have shown potential in Bayesian filtering. However, they still rely on particle-based representations of the posterior, which lose the rich information of the full distribution, or tackle a trajectory-level inverse problem that conflicts with the recursive structure of Bayesian filtering. To address this, we propose a new perspective of directly encoding the evolving distribution into flow matching model weights, namely, the Belief Flow Filter (BFF). It is a generative filtering framework that updates model weights via gradient descent at test time to track the posterior evolution. Thereby, BFF bypasses the scalability issue of particle representations or the flexibility limitation of Gaussian assumptions in conventional filters. We theoretically justify that the BFF design is structurally aligned with Bayesian filtering, and its training objective targets the recursive filtering operator. BFF is empirically verified across 5 different physical systems, including ones with chaotic dynamics and highly sparse, non-linear observations. The results show that BFF attains the best score in 8 of 9 metric-benchmark cells across the three standard 1D and 2D PDE benchmarks, and similarly leads on the extreme single-moving-sensor setting and on a real-world-grounded tokamak plasma estimation task, demonstrating its potential to accurately approximate the Bayesian filtering operator in high-dimensional probability space. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG). Categorie arXiv: Machine Learning (stat.ML) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.23383 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:58:09.580Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).