Metraipolis › archive › dc_0d09c0cc86fe
Non-Interfering Asymmetric AdamW Updates for Constrained Exploration of Equifinality in Hybrid Models — arXiv:2611.04756
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04756
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T21:51:45.035Z
- SHA-256 of the archived text
ce48525dc12e8943b66f0851d36ce2367bf28ea229565efbd855d1afbd82736d- Stable URL of this page
https://metraipolis.com/documento/dc_0d09c0cc86fe
How to cite
Non-Interfering Asymmetric AdamW Updates for Constrained Exploration of Equifinality in Hybrid Models — arXiv:2611.04756 — arXiv (en), https://arxiv.org/abs/2611.04756 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0d09c0cc86fe (Metraipolis archive dc_0d09c0cc86fe, sha256 ce48525dc12e8943b66f0851d36ce2367bf28ea229565efbd855d1afbd82736d)
BibTeX
@misc{dc0d09c0cc86fe,
title = {Non-Interfering Asymmetric AdamW Updates for Constrained Exploration of Equifinality in Hybrid Models — arXiv:2611.04756},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04756},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0d09c0cc86fe; sha256 ce48525dc12e8943b66f0851d36ce2367bf28ea229565efbd855d1afbd82736d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04756. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Hybrid models let neural networks supply the unresolved parameters of a process-based simulator, and are fitted to observations that constrain aggregate fluxes and storages but not the internal partitioning that produces them. Such a fit is equifinal: configurations indistinguishable in the observed aggregates can disagree substantially about the unobserved internals, and therefore about the mechanism they attribute to the same data. We study evapotranspiration, whose total flux is observed while its split into transpiration and evaporation is not. A model ensemble built from random seeds alone spans only a narrow band of the partitionings the data admit. We produce the spread deliberately, training members under auxiliary repulsion on transpiration, subject to the fit to observations not degrading. Non-interference is usually arranged by making the auxiliary gradient orthogonal to the main one, but under AdamW the applied step is a preconditioned momentum direction, so orthogonality between raw gradients no longer implies it. We introduce Non-interfering Asymmetric Network Optimization (NANO), an update whose first-order effect on the main loss is exactly that of the main objective alone, whose auxiliary step is bounded, and which concentrates repulsion in the coordinates the main gradient leaves idle. 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/2611.04756 — 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 2026-11-04T21:38:49.729Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).