English

Interpreting machine learning functions as physical observables

High Energy Physics - Lattice 2021-09-20 v1

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.

Keywords

Cite

@article{arxiv.2109.08497,
  title  = {Interpreting machine learning functions as physical observables},
  author = {Gert Aarts and Dimitrios Bachtis and Biagio Lucini},
  journal= {arXiv preprint arXiv:2109.08497},
  year   = {2021}
}

Comments

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

R2 v1 2026-06-24T06:04:20.857Z