Metraipolis › archive › dc_f15fe6d5bca4
Staged Depth Training: A Representation Curriculum for PINNs — arXiv:2609.30299
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30299
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T02:10:18.353Z
- SHA-256 of the archived text
0cab888e57c2ec7790d95252eca45f31c7feacc5272297b1ef7d9a4944df9841- Stable URL of this page
https://metraipolis.com/documento/dc_f15fe6d5bca4
How to cite
Staged Depth Training: A Representation Curriculum for PINNs — arXiv:2609.30299 — arXiv (en), https://arxiv.org/abs/2609.30299 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f15fe6d5bca4 (Metraipolis archive dc_f15fe6d5bca4, sha256 0cab888e57c2ec7790d95252eca45f31c7feacc5272297b1ef7d9a4944df9841)
BibTeX
@misc{dcf15fe6d5bca4,
title = {Staged Depth Training: A Representation Curriculum for PINNs — arXiv:2609.30299},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30299},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f15fe6d5bca4; sha256 0cab888e57c2ec7790d95252eca45f31c7feacc5272297b1ef7d9a4944df9841},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30299. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Representation quality is a central determinant of PINNs' performance, yet standard training leaves representations to emerge implicitly while fitting the final solution. We introduce \textbf{representation curriculum}, an ordered process in which representations are explicitly learned, transferred independently of their predictors, and progressively refined. We realize it with Staged Depth Training (SDT), which trains a shallow prefix under a temporary physics-informed head, discards the head, and freezes the learned prefix while adding depth, without equation-specific encodings or changes to the final architecture. Across the 20 default forward problems in PINNacle with three backbones, SDT improves 40 of 59 equal-budget problem--backbone cells by at least 5\% and remains within that band in the rest, with a 32.8\% geometric-mean error reduction on a PirateNet-style backbone. Mechanistic ablations suggest that the gain is not explained by optimizer restarts or shallow warm-starting alone. Representation visualizations and hyperparameter-basin analyses provide diagnostic evidence on representation geometry and local sensitivity to shared hyperparameters. On Poisson--Boltzmann 2D, SDT also more than doubles the fitted depth-scaling exponent for both backbones. These results support representation curriculum as a promising training strategy for improving PINNs while preserving the deployed architecture and inference cost.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computational Physics (physics.comp-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.30299 — 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 2026-10-08T01:43:06.647Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).