Metraipolis › archive › dc_66cd02c74483

Meta-learning accelerates detector design optimization — arXiv:2609.35827

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35827
License (as archived)
CC0-1.0
Archived
2026-10-07T17:32:24.044Z
SHA-256 of the archived text
35096d54858e786bbd06bf3ff8e975d47543181556ab60feff0899a11a9d5339
Stable URL of this page
https://metraipolis.com/documento/dc_66cd02c74483

How to cite

Meta-learning accelerates detector design optimization — arXiv:2609.35827 — arXiv (en), https://arxiv.org/abs/2609.35827 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66cd02c74483 (Metraipolis archive dc_66cd02c74483, sha256 35096d54858e786bbd06bf3ff8e975d47543181556ab60feff0899a11a9d5339)
BibTeX
@misc{dc66cd02c74483,
  title = {Meta-learning accelerates detector design optimization — arXiv:2609.35827},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35827},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66cd02c74483; sha256 35096d54858e786bbd06bf3ff8e975d47543181556ab60feff0899a11a9d5339},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35827. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The quality of a detector design is ultimately determined by the quality of the inference it enables, that is, by the accuracy with which the quantities of interest are reconstructed from the raw detector response. For complex detectors, the inference is performed by machine learning models, and the relation between the design and the attainable inference performance is, in general, non-trivial. In this work, we consider the optimization of the inference performance with respect to the detector design. The conventional approach prescribes retraining the inference model at every candidate design, thus, treating the evaluations as independent tasks and discarding the shared structure of the optimal inference algorithms at different designs. We propose the meta-learned objective estimate (MLOE): instead of solving the inference problem anew at every candidate design, a single meta-inference model, conditioned on the design and trained continually along the optimization path, is shared across all of them. We test MLOE on three families of optimization problems, the last of which comprises two design spaces of the Spectrometer Straw Tracker of the Search for Hidden Particles (SHiP) experiment; under matched budgets of simulation calls, the meta-inference model evaluates a candidate design using fewer simulation calls than the baseline strategies and holds the better rank over the convergence curve in all examined cases.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Instrumentation and Detectors (physics.ins-det) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.35827 — 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 2026-10-07T16:59:48.449Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).