Finite Asimov Sample Construction in Unbinned Neural Simulation-Based Inference
Abstract
Expected sensitivity calculations in frequentist analysis using neural simulation-based inference often require large simulated samples to approximate an unbinned Asimov dataset. We construct a finite weighted reference sample, for analyses based on learned density ratios, for which the generating parameters globally maximize the weighted likelihood. A toy example with five-dimensional observable space based loosely on high-energy physics models shows that an Asimov dataset consisting of as few as 256 weighted reference events closely reproduce the expected test statistic scans obtained with two million simulated reference events. The resulting test statistic distributions are also shown to agree with independent simulator-based pseudo-experiments. We note that this agreement with the simulator depends on the accuracy of the learned ratios and must be validated explicitly.
Related
- Simulation-Based Inference and Unbinned Asimov Construction with Hybrid Neural Density Estimation
- Spectroscopy of analogue black holes using simulation-based inference
- Amortized Simulation-Based Inference of Relativistic Mean-Field Couplings for Neutron-Star Equations of State
- Defining a Minimum Resolution for Unbinned Analyses
- Agentic Porting, Construction and Initial Verification and Validation of Libraries within the Open Source Unified TRAnsient Multi-Phase Advanced Reactor simulation Kit (Outram Park) Part I: A Software Engineering Log for Thermal Hydraulics
BibTeX
@misc{sa2026finite,
title = {{Finite Asimov Sample Construction in Unbinned Neural Simulation-Based Inference}},
author = {Rafael Coelho Lopes de Sa and Jay Sandesara},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.14136},
eprint = {2609.14136},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.14136},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Finite Asimov Sample Construction in Unbinned Neural Simulation-Based Inference
AU - Rafael Coelho Lopes de Sa
AU - Jay Sandesara
PY - 2026
DA - 2026/09/12
PB - arXiv
DO - 10.48550/arxiv.2609.14136
UR - https://arxiv.org/abs/2609.14136
AB - Expected sensitivity calculations in frequentist analysis using neural simulation-based inference often require large simulated samples to approximate an unbinned Asimov dataset. We construct a finite weighted reference sample, for analyses based on learned density ratios, for which the generating parameters globally maximize the weighted likelihood. A toy example with five-dimensional observable space based loosely on high-energy physics models shows that an Asimov dataset consisting of as few as 256 weighted reference events closely reproduce the expected test statistic scans obtained with two million simulated reference events. The resulting test statistic distributions are also shown to agree with independent simulator-based pseudo-experiments. We note that this agreement with the simulator depends on the accuracy of the learned ratios and must be validated explicitly.
ER -