Meta-learning accelerates detector design optimization
Abstract
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.
Related
- Transfer learning in bayesian optimization for aircraft design
- Machine learning-assisted design and explainable optimization of CdSnP2-based integrated solar-photodetector devices
- Physics-guided inverse design of Co-based superalloys using machine learning and multi-objective optimization for enhanced γ' solvus temperature
- Lead-free perovskite/HfSe2 surface plasmon resonance biosensor design via multi-metric optimization, Monte Carlo robustness analysis, and machine learning
- Optimization and Underground Implementation of the KAPAE Phase II Detector for an Invisible New Particle Search in Positronium Decay
BibTeX
@misc{borisyak2026metalearning,
title = {{Meta-learning accelerates detector design optimization}},
author = {Maxim Borisyak and Nikita Gladin and Andrey Ustyuzhanin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.35827},
eprint = {2609.35827},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.35827},
}
RIS
TY - UNPB
TI - Meta-learning accelerates detector design optimization
AU - Maxim Borisyak
AU - Nikita Gladin
AU - Andrey Ustyuzhanin
PY - 2026
DA - 2026/09/30
PB - arXiv
DO - 10.48550/arxiv.2609.35827
UR - https://arxiv.org/abs/2609.35827
AB - 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.
ER -