Metraipolis › archive › dc_6cc5267fef36
Structured Priors: Towards an algebra of component priors for prior-data fitted networks — arXiv:2611.04056
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04056
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T12:39:28.118Z
- SHA-256 of the archived text
ebc9e3a6c6b84aeab5910dece8b20aab2cc758456fd2bac83880d320f3248690- Stable URL of this page
https://metraipolis.com/documento/dc_6cc5267fef36
How to cite
Structured Priors: Towards an algebra of component priors for prior-data fitted networks — arXiv:2611.04056 — arXiv (en), https://arxiv.org/abs/2611.04056 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6cc5267fef36 (Metraipolis archive dc_6cc5267fef36, sha256 ebc9e3a6c6b84aeab5910dece8b20aab2cc758456fd2bac83880d320f3248690)
BibTeX
@misc{dc6cc5267fef36,
title = {Structured Priors: Towards an algebra of component priors for prior-data fitted networks — arXiv:2611.04056},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04056},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6cc5267fef36; sha256 ebc9e3a6c6b84aeab5910dece8b20aab2cc758456fd2bac83880d320f3248690},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04056. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Prior-data fitted networks are typically trained using synthetic data generated by a single, manually constructed generator. In cases where such a generator combines multiple components, e.g., in TabPFN, Mitra, or TabICLv2, this is achieved through a mixture using manually specified weights, the impact of which on the network only becomes apparent after pre-training. Instead of such a hand-built generator, this work proposes a structured prior: a small set of named component priors, linked by operators whose algebraic properties are formally proven and whose influence on the trained network has been validated. Within a measure-theoretic framework, the operators of mixture, convolution, amplitude scaling, local transform, and projection are defined. Their governing laws are proven. These operators are implemented in the macl2l software package. Experiments demonstrate that the implemented generators reproduce the identities within the resolution of a permutation test. Furthermore, it is shown that trained networks obey the distributive law; that a mixed prior composed of small components performs as well as or better than any individual component in seven out of eight open regression benchmarks; and that on two of these tables a structured prior reaches, with a ninth of the data budget, an error that a generic random-function prior does not reach even with the full budget. A theorem on model averaging demonstrates that networks trained on individual components constitute the Bayes predictor for the mixture, provided that the component networks are themselves the Bayes predictors for their respective priors. However, the pre-registered test of this averaged predictor with trained component networks failed, because the networks identify the generating component too rarely. The paper proposes a research program focused on the algebra of structured priors for prior-data fitted networks. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.04056 — 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 2026-11-04T12:29:47.268Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).