Metraipolis › archive › dc_4f4fa6611919

Bilevel Optimization of Topology and Hyperparameters (BOTH) — arXiv:2609.21758

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21758
License (as archived)
CC0-1.0
Archived
2026-10-10T01:45:13.325Z
SHA-256 of the archived text
e8f3f9ccce4c543709b6dc3d4f0485be09ea8d577800fc741e23ecb9663cde25
Stable URL of this page
https://metraipolis.com/documento/dc_4f4fa6611919

How to cite

Bilevel Optimization of Topology and Hyperparameters (BOTH) — arXiv:2609.21758 — arXiv (en), https://arxiv.org/abs/2609.21758 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f4fa6611919 (Metraipolis archive dc_4f4fa6611919, sha256 e8f3f9ccce4c543709b6dc3d4f0485be09ea8d577800fc741e23ecb9663cde25)
BibTeX
@misc{dc4f4fa6611919,
  title = {Bilevel Optimization of Topology and Hyperparameters (BOTH) — arXiv:2609.21758},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21758},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f4fa6611919; sha256 e8f3f9ccce4c543709b6dc3d4f0485be09ea8d577800fc741e23ecb9663cde25},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21758. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Topology optimization (TO) represents a significant step towards automating the design process: given a working simulation, TO can produce a viable prototype at the press of a button by differentiating the simulation and iteratively improving the design. In practice, however, TO is riddled with ``magic numbers''---hyperparameters whose tuning significantly affects the outcome. Finding the right values typically requires not only deep problem-specific knowledge but also extensive trial-and-error. While practitioners can use surrogate-assisted hyperparameter optimization as an alternative, this approach requires strictly limiting the number of hyperparameters through careful problem formulation. Here, we propose differentiating TO itself using automatic differentiation. This yields ``hypergradients'' that allow us to tune these hyperparameters in tandem with the primary optimization. We show that evaluating just one or two steps of TO is sufficiently informative and that the method scales favorably to thousands of hyperparameters at an expense comparable to only a few standard TO runs. We demonstrate this approach on stress-constrained and compliance problems, with the latter utilizing a neural parameterization of the density field.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.21758 — 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 2026-10-10T01:14:16.648Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).