cs.LGNov 3, 2026

Non-Interfering Asymmetric AdamW Updates for Constrained Exploration of Equifinality in Hybrid Models

Authors: Ekaterina Gikalo, Zavud Baghirov, Christian Reimers, Markus Reichstein, Martin Jung, Marco Körner

Organizations: Max Planck Institute for Biogeochemistry, Jena, Germany · TUM School of Engineering and Design, Technical University of Munich (TUM), Munich, Germany · ELLIS Unit Jena, Jena, Germany · German Remote Sensing Data Center (DFD), German Aerospace Center (DLR), Weßling, Germany

Abstract

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.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. EvE: An Alternate Optimizer to Adam

    Sep 28, 2026Shashank Raj, Kalyanmoy DebDeep Learning OptimizationDifferential Evolution

  2. From Hybrid Mechanistic--Data-Driven Modeling Toward Neuro-Symbolic AI: What, Why, and How

    Jul 24, 2026Moein E. Samadi, Andreas SchuppertNeuro-Symbolic AIEpistemic Uncertainty

  3. Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW

    Aug 20, 2026Kang Liu, Suyan LiNeural Network OptimizationNeural Network Training Dynamics