Machine-Learning-Based Method for Goodness-of-Fit Test in Amplitude Analysis

2025/04/23 by Huoyi Hou, Hou, Huoyi, Beijiang Liu +1 · 1 voice
Computer Science · Physics and Astronomy · #Anomaly Detection Techniques and Applications #hep-ex #physics.data-an

paper · pdf · doi:10.48550/arxiv.2504.17494

arxiv published 2025/04/23 · arxiv updated 2025/11/30

Abstract

Purpose: Amplitude analysis is a pivotal tool in hadron spectroscopy, fundamentally involving a series of likelihood fits to multi-dimensional experimental distributions. While robust goodness-of-fit tests exist for low-dimensional scenarios, evaluating goodness-of-fit in amplitude analysis remains challenging. Methods: We propose a machine-learning approach using anomaly detection for goodness-of-fit assessment in amplitude analysis. Our method employs a classifier to identify discrepancies between data and fit results in multi-dimensional phase space. Results and Conclusion: Using Monte Carlo simulations of J/ψ→γπ⁺π^-π⁰π⁰ decays, we demonstrate that this method detects contributions from an additional resonance with a signal strength of 1%. The detection power is sufficient for practical amplitude analyses, where contributions with fit fractions larger than 1% are typically included in the nominal fit. This approach shows promise for amplitude analyses of multi-body processes.

Citations

• The Belle II Physics Book
• XGBoost: A Scalable Tree Boosting System
• Covariant tensor formalism for partial wave analyses of psi decay to mesons

Discussions

• Huoyi Hou, Beijiang Liu: Goodness-of-fit for amplitude analysis with anomaly detection https://arxiv.org/abs/2504.17494 https://arxiv.org/pdf/2504.17494 https://arxiv.org/html/2504.17494 [bsky, 0 points, 1 comments]

Related

• Machine learning and multivariate goodness of fit
• Anomaly Detection for Resonant New Physics with Machine Learning
• Enhancing Sensitivity for Di-Higgs Boson Searches Using Anomaly Detection and Supervised Machine Learning Techniques
• B-Meson Anomalies: Effective Field Theory Meets Machine Learning
• Fast kernel methods for Data Quality Monitoring as a goodness-of-fit test