Interpreting machine learning functions as physical observables

2021/09/17 by Gert Aarts, Aarts, Gert, Dimitrios Bachtis +3
Computer Science · Materials Science · Physics and Astronomy · #FOS: Physical sciences #High Energy Physics - Lattice (hep-lat) #Machine Learning in Materials Science #Neural Networks and Applications #hep-lat

paper · pdf · doi:10.48550/arxiv.2109.08497

8 pages, contribution to the 38th International Symposium on Lattice Field Theory, 26th-30th July 2021, Massachusetts Institute of Technology, USA

arxiv created 2021/09/17 · openalex publication_date 2021/09/17 · arxiv updated 2021/09/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose to interpret machine learning functions as physical observables, opening up the possibility to apply "standard" statistical-mechanical methods to outputs from neural networks. This includes histogram reweighting and finite-size scaling, to analyse phase transitions quantitatively. In addition we incorporate predictive functions as conjugate variables coupled to an external field within the Hamiltonian of a system, allowing to induce order-disorder phase transitions in a novel manner. A noteworthy feature of this approach is that no knowledge of the symmetries in the Hamiltonian is required.

Related

• Neural Network Statistical Mechanics
• Machine learning phase transitions: Connections to the Fisher information
• Lecture Notes on Statistical Physics and Neural Networks
• Phase probabilities in first-order transitions using machine learning
• Machine Learned Phase Transitions in a System of Anisotropic Particles on a Square Lattice