Density-Guided Conditional Neural Processes for Detector Efficiency Estimation
Abstract
Selection efficiency connects observed counts to physical rates and rare-event search limits. With scarce calibration data, strong smoothing can erase sharp physical changes, while highly flexible models can overfit the data and mistake statistical fluctuations for physical structure. We introduce a density-guided conditional neural process (CNP) that uses spectral concentrations to control where high-frequency features are available. On MAJORANA data, it reconstructs local structure while matching measured efficiencies within twice their binomial statistical uncertainty in an average of 89% of bins across two continuum windows, versus 37% for Attentive CNP with positional encoding. With 5,000 efficiency-model training events and 500 context events, it exceeds CNP and Attentive CNP trained on twice as many events in both peak-core and continuum summaries, and also exceeds context-only KDE and Bernoulli GP. Our method thus balances the reconstruction of sharp physical features with resistance to statistical overfitting, and achieves this with fewer training events.
Related
- Polarization-insensitive high-efficiency superconducting nanowire single-photon detector
- The efficiency of moderating neutron detector: Monte Carlo simulation, experimental validation, and angular dependence
- Efficiency-Resolved Recovery Dynamics of an Free-Running InGaAs/InP Single Photon Avalanche Detector Operated in Gated Mode
- Detector Placement Relaxes Efficiency Requirements for Detecting a Weak Coherent Link
- Direct estimation of g(2)(0) from click statistics of a multiplexed detector
BibTeX
@misc{ma2026densityguided,
title = {{Density-Guided Conditional Neural Processes for Detector Efficiency Estimation}},
author = {Yue Ma and Aobo Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.13593},
eprint = {2609.13593},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.13593},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Density-Guided Conditional Neural Processes for Detector Efficiency Estimation
AU - Yue Ma
AU - Aobo Li
PY - 2026
DA - 2026/09/11
PB - arXiv
DO - 10.48550/arxiv.2609.13593
UR - https://arxiv.org/abs/2609.13593
AB - Selection efficiency connects observed counts to physical rates and rare-event search limits. With scarce calibration data, strong smoothing can erase sharp physical changes, while highly flexible models can overfit the data and mistake statistical fluctuations for physical structure. We introduce a density-guided conditional neural process (CNP) that uses spectral concentrations to control where high-frequency features are available. On MAJORANA data, it reconstructs local structure while matching measured efficiencies within twice their binomial statistical uncertainty in an average of 89% of bins across two continuum windows, versus 37% for Attentive CNP with positional encoding. With 5,000 efficiency-model training events and 500 context events, it exceeds CNP and Attentive CNP trained on twice as many events in both peak-core and continuum summaries, and also exceeds context-only KDE and Bernoulli GP. Our method thus balances the reconstruction of sharp physical features with resistance to statistical overfitting, and achieves this with fewer training events.
ER -