Abstract Markov Random Fields
Compositionality · 20.03.2026 · Volume 8 (2026)
DOI: 10.46298/compositionality-8-1 ↗Kurz gefasst
Fachartikel in der Zeitschrift Compositionality, online erschienen am 20.03.2026. Verfasst von Leon Lang und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Markov random fields are known to be fully characterized by properties of their information diagrams, or I-diagrams. In particular, for Markov random fields, regions in the I-diagram corresponding to disconnected vertex sets in the graph vanish. Recently, I-diagrams have been generalized to F-diagrams, for a larger class of functions F satisfying the chain rule beyond Shannon entropy, such as Kullback-Leibler divergence and cross-entropy. In this work, we generalize the notion and characterization of Markov random fields to this larger class of functions F and investigate preliminary applications. We define F-independences, F-mutual independences, and F-Markov random fields and characterize them by their F-diagram. In the process, we also define F-dual total correlation and prove that its vanishing is equivalent to F-mutual independence. We then apply our results to information functions F that are applied to probability mass functions. We show that if the probability distributions of a set of random variables are Markov random fields for the same graph, then we formally recover the notion of an F-Markov random field for that graph. We then study the Kullback-Leibler diagrams on specific Markov chains, leading to a visual representation of the second law of thermodynamics and a simple explicit derivation of the decomposition of the evidence lower bound for diffusion models. 56 pages, 9 figures
Zitieren
APA
Lang, L., Mulatier, C. D., Quax, R., & Forré, P. (2026). Abstract Markov Random Fields. Compositionality, Volume 8 (2026). https://doi.org/10.46298/compositionality-8-1
Vancouver
Lang L, Mulatier CD, Quax R, Forré P. Abstract Markov Random Fields. Compositionality. 2026;Volume 8 (2026). doi:10.46298/compositionality-8-1
BibTeX
@article{Lang2026,
author = {Lang, Leon and Mulatier, Clélia de and Quax, Rick and Forré, Patrick},
title = {Abstract Markov Random Fields},
journal = {Compositionality},
year = {2026},
volume = {Volume 8 (2026)},
doi = {10.46298/compositionality-8-1}
}
EUVIMED