Machine learning the Ising transition: A comparison between discriminative and generative approaches

Abstract

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.

11+5 pages, 4+4 figures

References in corpus (22)

• Machine learning and the physical sciences
• Machine learning phases of matter
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Quantum Loop Topography for Machine Learning
• Provably efficient machine learning for quantum many-body problems
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Machine learning vortices at the Kosterlitz-Thouless transition
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Kernel methods for interpretable machine learning of order parameters
• Asymptotically unbiased estimation of physical observables with neural samplers
• Unsupervised phase discovery with deep anomaly detection
• Unsupervised machine learning of topological phase transitions from experimental data
• Divergence of predictive model output as indication of phase transitions
• Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence
• Quantum kernels to learn the phases of quantum matter
• Interpretable and unsupervised phase classification
• Visualizing Quantum Phases And Identifying Quantum Phase Transitions By Nonlinear Dimensionality Reduction
• Enhancing variational Monte Carlo using a programmable quantum simulator
• Mapping out phase diagrams with generative classifiers
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks