Abstract:jNO (jax Neural Operators) is a JAX-native library for neural operators and foundation models with unified support for both data-driven and physics-informed training. Its core design is a tracing system in which domains, model calls, residuals, supervised losses, and diagnostics are written in one symbolic language and compiled into one optimization pipeline. This allows users to move between operator regression, mesh-aware residual evaluation, and PDE-constrained training without restructuring the surrounding code. jNO also supports multi-model compositions, fine-grained control at parameter level (model, optimizer, and learning rate), hyperparameter tuning, and JAX-native workflows for translated PDE foundation-model families. The source repository is available at this https URL.
| Subjects: | Machine Learning (cs.LG); Numerical Analysis (math.NA); Computational Physics (physics.comp-ph) |
| Cite as: | arXiv:2605.10159 [cs.LG] |
| (or arXiv:2605.10159v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10159 arXiv-issued DOI via DataCite (pending registration) |
From: Leon Armbruster [view email]
[v1]
Mon, 11 May 2026 08:05:54 UTC (881 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。