Metraipolis › archive › dc_bc02e8f36855

Bayesian Optimisation under State-Preservation Constraints — arXiv:2610.12150

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12150
License (as archived)
CC0-1.0
Archived
2026-10-09T06:23:39.472Z
SHA-256 of the archived text
b58ae8242b834993c0670942544f9973c8db024ed89abdf18425bb8097ce5616
Stable URL of this page
https://metraipolis.com/documento/dc_bc02e8f36855

How to cite

Bayesian Optimisation under State-Preservation Constraints — arXiv:2610.12150 — arXiv (en), https://arxiv.org/abs/2610.12150 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc02e8f36855 (Metraipolis archive dc_bc02e8f36855, sha256 b58ae8242b834993c0670942544f9973c8db024ed89abdf18425bb8097ce5616)
BibTeX
@misc{dcbc02e8f36855,
  title = {Bayesian Optimisation under State-Preservation Constraints — arXiv:2610.12150},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12150},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc02e8f36855; sha256 b58ae8242b834993c0670942544f9973c8db024ed89abdf18425bb8097ce5616},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12150. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In many engineering design problems, the objective and constraints depend on the state: the solution of a PDE determined by the design parameters. We consider improving a design while holding selected state observables near trusted values, which we call state preservation constraints. Constrained Bayesian optimisation handles these with a learnt feasibility model, but struggles with this problem's highly anisotropic feasible set. Our central idea is to pre-compute the set of controls whose linearised constraint response stays within tolerance, thereby pulling back the state-space constraint into design space. This linearisation defines an ellipsoid from which we can efficiently draw a large number of well-spread candidates. The underlying linear response map is refined online, and the ellipsoid is rebuilt accordingly. We demonstrate the method end-to-end on our key application - Tokamak divertor optimisation under plasma-boundary preservation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.12150 — 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 2026-10-09T05:50:31.711Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).