Exploring new directions in enhancing the ACTS parameter optimization suite
Abstract
Track seeding strongly affects both the quality and computational cost of charged-particle reconstruction, yet its many configuration parameters are commonly tuned through expert intuition and repeated trial and error. ACTS reduces this burden with an Optuna Tree-structured Parzen Estimator auto-tuner, but expensive evaluations, a restricted search space, and a scalarized objective can limit evaluation efficiency, exclude promising configurations, and obscure performance trade-offs. We investigate whether Bayesian optimization can address these limitations using ACTS with the Open Data Detector (ODD). Under identical search ranges and a common 100-trial budget, we compare Expected Improvement and Upper Confidence Bound with TPE and random search on the existing eight-parameter problem, extend the best-performing Bayesian method to fifteen parameters, and apply Expected Hypervolume Improvement to optimize efficiency, fake rate, duplicate rate, and runtime without fixed scalar weights. Candidate configurations are evaluated through the full ACTS reconstruction chain and validated on disjoint held-out events. The Bayesian acquisition methods identify strong configurations earlier than TPE, and their advantage persists in held-out validation. Expanding the search further improves performance, while multi-objective optimization reveals competitive non-dominated solutions spanning distinct trade-offs. These results indicate that Bayesian optimization can strengthen ACTS auto-tuning through efficient evaluation, broader parameter searches, and post-hoc expert selection among non-dominated alternatives.
Related
- Exploring multi-parameter optimization in FRG
- Active-subspace learning reveals dominant parameter directions in nuclear observables
- Enhancing light-matter coupling for exploring chaos in the quantum Rabi model
- Multi-band cross-correlation dark sirens: enhancing cosmological parameter and gravitational-wave bias constraints
- Selecting movements for muscle parameter estimation: insights from gradient analysis in trajectory optimization
BibTeX
@misc{lavoie2026exploring,
title = {{Exploring new directions in enhancing the ACTS parameter optimization suite}},
author = {Chance LaVoie and Qi Bin Lei and Rocky Bala Garg and Lauren Tompkins},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.14714},
eprint = {2608.14714},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.14714},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Exploring new directions in enhancing the ACTS parameter optimization suite
AU - Chance LaVoie
AU - Qi Bin Lei
AU - Rocky Bala Garg
AU - Lauren Tompkins
PY - 2026
DA - 2026/08/11
PB - arXiv
DO - 10.48550/arxiv.2608.14714
UR - https://arxiv.org/abs/2608.14714
AB - Track seeding strongly affects both the quality and computational cost of charged-particle reconstruction, yet its many configuration parameters are commonly tuned through expert intuition and repeated trial and error. ACTS reduces this burden with an Optuna Tree-structured Parzen Estimator auto-tuner, but expensive evaluations, a restricted search space, and a scalarized objective can limit evaluation efficiency, exclude promising configurations, and obscure performance trade-offs. We investigate whether Bayesian optimization can address these limitations using ACTS with the Open Data Detector (ODD). Under identical search ranges and a common 100-trial budget, we compare Expected Improvement and Upper Confidence Bound with TPE and random search on the existing eight-parameter problem, extend the best-performing Bayesian method to fifteen parameters, and apply Expected Hypervolume Improvement to optimize efficiency, fake rate, duplicate rate, and runtime without fixed scalar weights. Candidate configurations are evaluated through the full ACTS reconstruction chain and validated on disjoint held-out events. The Bayesian acquisition methods identify strong configurations earlier than TPE, and their advantage persists in held-out validation. Expanding the search further improves performance, while multi-objective optimization reveals competitive non-dominated solutions spanning distinct trade-offs. These results indicate that Bayesian optimization can strengthen ACTS auto-tuning through efficient evaluation, broader parameter searches, and post-hoc expert selection among non-dominated alternatives.
ER -