Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
This work provides a theoretical validation for using neural networks in phase transition analysis, which is incremental as it builds on existing scaling theories but applies them to machine learning contexts.
The authors tackled the problem of connecting supervised learning of phase classification in the Ising model to finite-size-scaling theory, showing that a minimal one-parameter neural network can theoretically validate the emergence of universal scaling functions and predict critical points for unseen data from different lattices in the same universality class.
We investigate the connection between the supervised learning of the binary phase classification in the ferromagnetic Ising model and the standard finite-size-scaling theory of the second-order phase transition. Proposing a minimal one-free-parameter neural network model, we analytically formulate the supervised learning problem for the canonical ensemble being used as a training data set. We show that just one free parameter is capable enough to describe the data-driven emergence of the universal finite-size-scaling function in the network output that is observed in a large neural network, theoretically validating its critical point prediction for unseen test data from different underlying lattices yet in the same universality class of the Ising criticality. We also numerically demonstrate the interpretation with the proposed one-parameter model by providing an example of finding a critical point with the learning of the Landau mean-field free energy being applied to the real data set from the uncorrelated random scale-free graph with a large degree exponent.