Metraipolis › archive › dc_d49715bb130f

Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level… — arXiv:2608.16473

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16473
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:39.089Z
SHA-256 of the archived text
25d783bb297de5db940558cc0aa3ae7ad7680c4bdff46f8817dcd40e3d777fde
Stable URL of this page
https://metraipolis.com/documento/dc_d49715bb130f

How to cite

Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level… — arXiv:2608.16473 — arXiv (en), https://arxiv.org/abs/2608.16473 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d49715bb130f (Metraipolis archive dc_d49715bb130f, sha256 25d783bb297de5db940558cc0aa3ae7ad7680c4bdff46f8817dcd40e3d777fde)
BibTeX
@misc{dcd49715bb130f,
  title = {Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level… — arXiv:2608.16473},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16473},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d49715bb130f; sha256 25d783bb297de5db940558cc0aa3ae7ad7680c4bdff46f8817dcd40e3d777fde},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16473. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Neural PDE training yields a finite checkpoint archive, yet its logged energy errors are inaccessible without the exact solution, while loss-based selection does not necessarily recover the logged energy oracle. For admissible neural approximations of symmetric coercive variational problems, we introduce a reference-free selection rule based on minimizing a computable conforming Riesz monitor. The exact residual-energy identity and conforming projection make the monitor an unconditional lower bound converging monotonically to each logged energy error under nested conforming refinement; under saturation, hierarchical enrichment yields a computable upper estimate and hence a lower-upper bracket. A key finding is that archive selection is order-sensitive: unresolved checkpoint-dependent components can reverse the oracle-non-oracle ranking at finite resolution, so checkpointwise recovery alone is insufficient. For finite archives, we prove uniform recovery, yielding convergence to the logged-oracle error and, without saturation, logged-oracle selection at sufficiently fine auxiliary resolution. Under saturation, the bracket gives a computable near-oracle bound and certifies unique logged-oracle selection upon interval separation. We also bound logging-resolution loss and certify oracle inclusion over prescribed comparison trajectories. The resulting criterion replaces inaccessible exact-error minimization by computable, training-independent post-training selection on the intrinsic energy-error scale, requiring only the computed candidates and the variational problem. Experiments on diffusion and elasticity, including a non-manufactured perforated plate, demonstrate energy-scale calibration, oracle-level selection, and modest post-processing cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA).
Pagina del lavoro: https://arxiv.org/abs/2608.16473 — 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 2026-10-18T19:02:44.176Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).