Physically Consistent Parameter Inference: Transparent Machine Learning Emulation in High Energy Physics and Cosmology
hep-ph, cs.LG
Submitted: 2026-07-14
Updated: 2026-09-08
Comments: 33 pages, 15 figures, 6 tables. Matches published version
Journal ref: Universe 12 (2026) 238
Code: https://github.com/Jorge-Alda/SMEFT19
License: http://creativecommons.org/licenses/by/4.0/
The gist: Global fits in high energy physics and cosmology often face the challenge of exploring high-dimensional parameter spaces with computationally expensive or topologically complex likelihood functions.
Terminology
Abstract
Global fits in high energy physics and cosmology often face the challenge of exploring high-dimensional parameter spaces with computationally expensive or topologically complex likelihood functions. In this work, we present a Machine Learning framework designed to emulate complex, often non-Gaussian likelihood landscapes using gradient-boosted regression trees (XGBoost). We discuss the advantages of the Machine Learning approach in terms of computational efficiency and the resolution of confidence regions, particularly in scenarios with complex correlations or "curved" degeneracies. We validate this methodology by applying it to a recent analysis on flavour anomalies in semileptonic B meson decays and discussing the adaptability of this framework to other phenomenological systems, such as axion-like particles or cosmology global fits. Finally, we utilise SHAP (Shapley Additive exPlanations) values to provide a transparent analysis of feature importance, ensuring that the Machine Learning predictions remain physically interpretable and consistent with the underlying physics.
Sources
- Using Machine Learning techniques in phenomenological studies in flavour physics
- Anomalies in B mesons decays: A phenomenological approach
- Exploring B-physics anomalies at colliders
- Flavour Anomalies: A comparative analysis using a machine learning algorithm
- B-Meson Anomalies: Effective Field Theory Meets Machine Learning
- Lecture notes on Machine Learning applications for global fits
- XGBoost: A Scalable Tree Boosting System
- A Unified Approach to Interpreting Model Predictions
- Consistent Individualized Feature Attribution for Tree Ensembles
- Optuna: A Next-generation Hyperparameter Optimization Framework
- Measurement of the ratio of branching fractions $\mathcal{B}(B_c^+\,\to\,J/\psi\tau^+\nu_\tau)$/$\mathcal{B}(B_c^+\,\to\,J/\psi\mu^+\nu_\mu)$
- Test of lepton universality in beauty-quark decays
- Evidence for $B^{+}\to K^{+}\nu\bar{\nu}$ decays
- flavio: a Python package for flavour and precision phenomenology in the Standard Model and beyond
- A Global Likelihood for Precision Constraints and Flavour Anomalies
- Wilson: a Python package for the running and matching of Wilson coefficients above and below the electroweak scale
- Measurement of the ratio of the B$_\mathrm{c}^+$ $\to$ J/$\psi$$\tau^+\nu_\tau$ and B$_\mathrm{c}^+$ $\to$ J/$\psi$ $\mu^+\nu_\mu$ branching fractions using three-prong $\tau$ lepton decays
- Displaced or invisible? ALPs from $B$ decays at Belle II
- Global Analysis of the ALP Effective Theory
- Comprehensive ALP Searches in Meson Decays
Related papers
- Classification of g-modes for neutron stars with a strong transition: Novel universal relation including slow stable hybrid stars
- Higgsino Dark Matter Interpretation of the LUX-ZEPLIN 248 keV Nuclear-Recoil Event
- A Unified Bogoliubov Approach to Primordial Gravitational Waves: From Inflation to Reheating
- Probing Memory-Burdened Primordial Black Holes with High-Energy Neutrinos
- Enhanced Dark Matter Quantum Sensing via Phase-Space Geometric Interferometry
- Axions as Dark Matter, Dark Energy, and Dark Radiation