Interpretable machine learning in Physics

Abstract

Adding interpretability to multivariate methods creates a powerful synergy for exploring complex physical systems with higher order correlations while bringing about a degree of clarity in the underlying dynamics of the system.

arXiv commentSubmitted version of invited Comment Article for Nature Reviews Physics (2022)

References in corpus (3)

• XGBoost: A Scalable Tree Boosting System
• Interpretable machine learning: definitions, methods, and applications
• Deep Learning and its Application to LHC Physics

Cited by in corpus (9)

• Constraints on the trilinear and quartic Higgs couplings from triple Higgs production at the LHC and beyond
• A Detailed Study of Interpretability of Deep Neural Network based Top Taggers
• Machine learning the trilinear and light-quark Yukawa couplings from Higgs pair kinematic shapes
• Beyond Cuts in Small Signal Scenarios -- Enhanced Sneutrino Detectability Using Machine Learning
• Identifying Dominant Industrial Sectors in Market States of the S&P 500 Financial Data
• Boosted top tagging and its interpretation using Shapley values
• Probing the Inert Doublet Model via Vector-Boson Fusion at a Muon Collider
• Prospects for exotic $h\to 4\tau$ decays in single and di-Higgs boson production at the LHC and future hadron colliders
• The Physics Behind ML-based Quark-Gluon Taggers