Metraipolis › archive › dc_265028bcfdce
Information Geometry of Message Passing — arXiv:2608.15922
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15922
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T18:04:50.570Z
- SHA-256 of the archived text
382ad9f8d8884a41bf8b7bdf18e31b13c7dbac97d24aa877f8856cf43efe089c- Stable URL of this page
https://metraipolis.com/documento/dc_265028bcfdce
How to cite
Information Geometry of Message Passing — arXiv:2608.15922 — arXiv (en), https://arxiv.org/abs/2608.15922 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_265028bcfdce (Metraipolis archive dc_265028bcfdce, sha256 382ad9f8d8884a41bf8b7bdf18e31b13c7dbac97d24aa877f8856cf43efe089c)
BibTeX
@misc{dc265028bcfdce,
title = {Information Geometry of Message Passing — arXiv:2608.15922},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15922},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_265028bcfdce; sha256 382ad9f8d8884a41bf8b7bdf18e31b13c7dbac97d24aa877f8856cf43efe089c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15922. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We show that the natural-gradient stationary condition of variational inference has an edge-local form on a Forney-style factor graph. We start from the Bethe free energy and constrain a selected edge marginal to an exponential family. At a stationary point, the natural parameter of that edge equals the sum of two projected messages, one from each incident factor. Each projected message is the natural-gradient projection of the exact belief-propagation log-message at the current receiving marginal, or equivalently, the gradient of its expectation in the so-called mean coordinates. We call the resulting scheme natural-gradient message passing (NGMP). The rule is local; each edge may carry its own exponential family, and the message a factor sends depends on the marginal that receives it. Compared with variational message passing, NGMP keeps the part of the exact message that the receiving family can represent instead of averaging the factor under the neighboring beliefs. The two coincide when the uncertainty on the edges entering a non-conjugate factor vanishes, and NGMP is more accurate when that uncertainty persists, for example, along a partially observed latent chain or when parameters are filtered through successive data batches. Experiments on Poisson smoothing, heteroskedastic regression, and hourly ETTh forecasting confirm this and show that the gain appears mainly in uncertainty calibration. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.15922 — 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 2026-10-18T16:29:14.062Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).