Metraipolis › archive › dc_4349bc304407

From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs — arXiv:2608.04206

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04206
License (as archived)
CC0-1.0
Archived
2026-10-31T11:34:41.699Z
SHA-256 of the archived text
787cc155c8cd1d023bca66717ec9e5dbb297bfafabaf1d5199c287f13280fd3e
Stable URL of this page
https://metraipolis.com/documento/dc_4349bc304407

How to cite

From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs — arXiv:2608.04206 — arXiv (en), https://arxiv.org/abs/2608.04206 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4349bc304407 (Metraipolis archive dc_4349bc304407, sha256 787cc155c8cd1d023bca66717ec9e5dbb297bfafabaf1d5199c287f13280fd3e)
BibTeX
@misc{dc4349bc304407,
  title = {From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs — arXiv:2608.04206},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04206},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4349bc304407; sha256 787cc155c8cd1d023bca66717ec9e5dbb297bfafabaf1d5199c287f13280fd3e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04206. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Physics-informed neural networks (PINNs) often require high-accuracy quasi-Newton refinement to obtain reliable partial differential equation solutions, but their residual objectives can exhibit indefinite, nearly singular, and poorly scaled local curvature. Regularized quasi-Newton methods provide established mechanisms for stabilizing secant models, while self-concordant methods provide local-metric rules for curvature-dependent step selection. Building on these two lines of work, we propose SCORE, a self-concordance-inspired quasi-Newton method with decrement-coupled shifted secant geometry for PINN training. Its distinguishing mechanism is that a single quasi-Newton decrement computed from the learned inverse metric jointly determines a strong-Wolfe-tested candidate step and an adaptive shift used to define the next secant geometry. The shifted displacement represents the action of an averaged shifted metric along the accepted step, while requiring neither Hessian construction nor Hessian-vector products. Under a local spectral-equivalence condition, we show that the quasi-Newton decrement and candidate step remain comparable to their counterparts in a positive shifted metric, and recover the normalized self-concordant rule in the matched-metric case. Strong Wolfe acceptance, fallback line search, and standard curvature safeguards provide globalization without modifying the underlying PINN objective. Experiments on the viscous Burgers, Kuramoto--Sivashinsky, Korteweg--de Vries, and complex Ginzburg--Landau equations show that SCORE attains lower final errors than the tested BFGS and self-scaled Broyden baselines. The Burgers ablation further indicates that shifted curvature stabilization and decrement-based step selection make complementary contributions to high-accuracy refinement.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.04206 — 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 2026-10-31T11:24:48.764Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).