Lecture notes on Machine Learning applications for global fits
hep-ph, cs.LG
Submitted: 2026-04-08
Updated: 2026-07-16
Comments: Lecture notes for the 4th COMCHA School on Computing Challenges in Zaragoza (Spain), 8-15 April 2026. 25 pages, 10 figures, 14 code snippets, 1 appendix. Submission to SciPost Physics Lecture Notes. Fixed minor typos and improved visual presentation of figures
Journal ref: SciPost Phys. Lect. Notes 135 (2026)
DOI: 10.21468/SciPostPhysLectNotes.135
License: http://creativecommons.org/licenses/by/4.0/
The gist: These lecture notes provide a comprehensive framework for performing global statistical fits in high-energy physics using modern Machine Learning (ML) surrogates.
Terminology
Abstract
These lecture notes provide a comprehensive framework for performing global statistical fits in high-energy physics using modern Machine Learning (ML) surrogates. We begin by reviewing the statistical foundations of model building, including the likelihood function, Wilks' theorem, and profile likelihoods. Recognizing that the computational cost of evaluating model predictions often renders traditional minimization prohibitive, we introduce Boosted Decision Trees to approximate the log-likelihood function. The notes detail a robust ML workflow including efficient generation of training data with active learning and Gaussian processes, hyperparameter optimization, model compilation for speed-up, and interpretability through SHAP values to decode the influence of model parameters and interactions between parameters. We further discuss posterior distribution sampling using Markov Chain Monte Carlo (MCMC). These techniques are finally applied to the B plus or minus to K plus or minus ν ν anomaly at Belle II, demonstrating how a two-stage ML model can efficiently explore the parameter space of Axion-Like Particles (ALPs) while satisfying stringent experimental constraints on decay lengths and flavor-violating couplings.
Sources
- Using Machine Learning techniques in phenomenological studies in flavour physics
- Flavour Anomalies: A comparative analysis using a machine learning algorithm
- B-Meson Anomalies: Effective Field Theory Meets Machine Learning
- Asymptotic formulae for likelihood-based tests of new physics
- Active Learning and Bayesian Optimization: a Unified Perspective to Learn with a Goal
- A Framework for Interdomain and Multioutput Gaussian Processes
- XGBoost: A Scalable Tree Boosting System
- A Unified Approach to Interpreting Model Predictions
- Consistent Individualized Feature Attribution for Tree Ensembles
- shapiq: Shapley Interactions for Machine Learning
- emcee: The MCMC Hammer
- Evidence for $B^{+}\to K^{+}\nu\bar{\nu}$ decays
- Minimal Flavor Violation with Axion-like Particles
- Quark Flavor Phenomenology of the QCD Axion
- Running in the ALPs
- The Low-Energy Effective Theory of Axions and ALPs
- One-loop corrections to ALP couplings
- Running beyond ALPs: shift-breaking and CP-violating effects
- Renormalization of effective field theories via on-shell methods: the case of axion-like particles
- Light New Physics in $B\to K^{(*)}\nu\bar\nu$?
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