Metraipolis › archive › dc_575f67e53159
Instrumental Transfer Learning for Solution Operators — arXiv:2610.41262
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41262
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T08:14:35.966Z
- SHA-256 of the archived text
d3d317e322eb0abddc7d709ca5bfe05a832b8ff4fba9dd4d92ca66f32f1aab63- Stable URL of this page
https://metraipolis.com/documento/dc_575f67e53159
How to cite
Instrumental Transfer Learning for Solution Operators — arXiv:2610.41262 — arXiv (en), https://arxiv.org/abs/2610.41262 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_575f67e53159 (Metraipolis archive dc_575f67e53159, sha256 d3d317e322eb0abddc7d709ca5bfe05a832b8ff4fba9dd4d92ca66f32f1aab63)
BibTeX
@misc{dc575f67e53159,
title = {Instrumental Transfer Learning for Solution Operators — arXiv:2610.41262},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41262},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_575f67e53159; sha256 d3d317e322eb0abddc7d709ca5bfe05a832b8ff4fba9dd4d92ca66f32f1aab63},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41262. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Data-driven learning for the solution operator of a differential equation has broad scientific importance, but observations from a target system are often scarce and costly to collect. Related source systems may provide abundant observations under similar physical conditions, whereas even small changes in the governing equation can induce complex changes in the solution operator, making naive data pooling ineffective. We propose a structured transfer learning method that accounts for unknown sparse differences in the governing equations from a known library of candidate terms. Using the resolvent identity and a whitened instrumental variable approach, we construct unbiased source estimating equations for the target operator. Building on these equations, we develop a three-stage estimator that consists of a target-only ridge pilot, source-wise sparse calibration, and a projected refit designed to remove the leading calibration error inherited from the pilot. An iterative recalibration scheme further reduces the remaining error. We establish non-asymptotic prediction bounds showing when transfer achieves the pooled all-source rate, together with minimax lower bounds that characterize both rate optimality and fundamental identifiability limits under common shifts. Simulations and an electronic band-pass filter application demonstrate clear gains over target-only learning, naive pooling and existing transfer methods. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ML, nuovi lavori del giorno). Categorie arXiv: Methodology (stat.ME) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.41262 — 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 2026-11-03T08:03:23.768Z dalla pagina https://arxiv.org/list/stat.ML/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).