Machine learning the Ising transition: A comparison between discriminative and generative approaches
This work addresses the selection of machine learning methods for phase classification in physics, but it is incremental as it focuses on a specific model without broad new insights.
The study tackled the problem of detecting phase transitions in many-body physics by comparing discriminative and generative machine learning approaches, finding that the choice depends on factors like dataset size and computational resources.
The detection of phase transitions is a central task in many-body physics. To automate this process, the task can be phrased as a classification problem. Classification problems can be approached in two fundamentally distinct ways: through either a discriminative or a generative method. In general, it is unclear which of these two approaches is most suitable for a given problem. The choice is expected to depend on factors such as the availability of system knowledge, dataset size, desired accuracy, computational resources, and other considerations. In this work, we answer the question of how one should approach the solution of phase-classification problems by performing a numerical case study on the thermal phase transition in the classical two-dimensional square-lattice ferromagnetic Ising model.