Meta-learning accelerates detector design optimization

2026-09-22

AI Summary

This study addresses the computational bottleneck arising from repeatedly retraining inference models during complex detector design optimization. To this end, we propose Meta-Learning Objective Estimation (MLOE), a method that leverages conditional neural networks and continual learning strategies to construct a unified meta-inference model conditioned on design parameters. By uncovering shared structures among optimal inference algorithms across different designs, MLOE eliminates the need for independent retraining and enables efficient knowledge transfer along continuous optimization trajectories. Experimental evaluations in scenarios such as SHiP demonstrate that, under equivalent computational budgets, MLOE substantially reduces the number of required simulation calls while consistently maintaining superior design rankings throughout the convergence process.

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.

Problem

• detector design optimization
• meta-learning
• inference performance
• simulation efficiency

Innovation

• Meta-learning
• Detector design optimization
• MLOE
• Continual training
• Simulation efficiency