Interpretable and unsupervised phase classification

Abstract

Fully automated classification methods that yield direct physical insights into phase diagrams are of current interest. Here, we demonstrate an unsupervised machine learning method for phase classification which is rendered interpretable via an analytical derivation of its optimal predictions and allows for an automated construction scheme for order parameters. Based on these findings, we propose and apply an alternative, physically-motivated, data-driven scheme which relies on the difference between mean input features. This mean-based method is computationally cheap and directly interpretable. As an example, we consider the physically rich ground-state phase diagram of the spinless Falicov-Kimball model.

arXiv comment6+12 pages, 3+7 figures

References in corpus (62)

• Machine learning and the physical sciences
• Machine learning phases of matter
• Quantum Cluster Theories
• A high-bias, low-variance introduction to Machine Learning for physicists
• Nonequilibrium dynamical mean-field theory and its applications
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Dynamical phase transition in correlated fermionic lattice systems
• Exact solution of the Falicov-Kimball model with dynamical mean-field theory
• Nonequilibrium dynamical mean-field theory
• Identifying topological order through unsupervised machine learning
• Machine Learning Phases of Strongly Correlated Fermions
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Disorder-Free Localization
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Nonthermal steady states after an interaction quench in the Falicov-Kimball model
• Unsupervised machine learning and band topology
• Tunable Giant Exchange Bias in an Intercalated Transition Metal Dichalcogenide
• Machine Learning for Quantum Matter
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Unsupervised Manifold Clustering of Topological Phononics
• Topological quantum phase transitions retrieved through unsupervised machine learning
• Unsupervised machine learning of topological phase transitions from experimental data
• Thermodynamics of the two-dimensional Falicov-Kimball model: a classical Monte Carlo study
• Stripe phases in the two-dimensional Falicov-Kimball model
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Unsupervised identification of topological order using predictive models
• Generic optical excitations of correlated systems: $\pi$-tons
• Learning multiple order parameters with interpretable machines
• Simple ${\mathbb{Z}}_2$ lattice gauge theories at finite fermion density
• Interaction-tuned Anderson versus Mott localization
• Spin and charge pumping by steady or pulse current-driven magnetic domain wall: A self-consistent multiscale time-dependent-quantum/time-dependent-classical approach
• Low rank compression in the numerical solution of the nonequilibrium Dyson equation
• Nonlocal correlations and spectral properties of the Falicov-Kimball model
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Interpreting machine learning of topological quantum phase transitions
• Divergence of predictive model output as indication of phase transitions
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Unsupervised learning using topological data augmentation
• Pattern formation in mixtures of ultracold atoms in optical lattices
• Charge stripes due to electron correlations in the two-dimensional spinless Falicov-Kimball model
• Phase Detection with Neural Networks: Interpreting the Black Box
• Fractionalized Metal in a Falicov-Kimball Model
• Nonequilibrium perturbation theory of the spinless Falicov-Kimball model
• Formation of charge and spin ordering in strongly correlated electron systems
• Charge density wave and charge pump of interacting fermions in circularly shaken hexagonal optical lattices
• Nonequilibrium Dynamical Cluster Approximation study of the Falicov-Kimball Model
• Local correlation functions of arbitrary order for the Falicov-Kimball model
• Temperature-driven gapless topological insulator
• Real-space cluster dynamical mean-field approach to the Falicov-Kimball model: An alloy-analogy approach
• Spreading of correlations in the Falicov-Kimball model
• Nonequilibrium charge transport through Falicov-Kimball structures connected to metallic leads
• Momentum distribution and ordering in mixtures of ultracold light and heavy fermionic atoms
• Generalized Falicov-Kimball Models
• Gapless regime in the charge density wave phase of the finite dimensional Falicov-Kimball model
• Universal dielectric response across a continuous metal-insulator transition
• Electronic transport through correlated electron systems with nonhomogeneous charge orderings
• Classical and quantum liquids induced by quantum fluctuations
• Anderson localization on Falicov-Kimball model with next-nearest-neighbor hopping and long-range correlated disorder

Cited by in corpus (19)

• Quantitative and Interpretable Order Parameters for Phase Transitions from Persistent Homology
• Machine learning discovery of new phases in programmable quantum simulator snapshots
• Mott transition in a cavity-boson system: A quantitative comparison between theory and experiment
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Mapping out phase diagrams with generative classifiers
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Adversarial Machine Learning Phases of Matter
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• Machine learning of phases and structures for model systems in physics
• Phase determination with and without deep learning
• Probing phase transitions with correlations in configuration space
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Fluctuation based interpretable analysis scheme for quantum many-body snapshots
• Unsupervised Machine Learning Phase Classification for Falicov-Kimball Model
• Machine learning the Ising transition: A comparison between discriminative and generative approaches
• Supervised learning of an interacting 2D hard-core boson model of a weak topological insulator using correlation functions
• Optimized Observable Readout from Single-shot Images of Ultracold Atoms via Machine Learning
• Snake net and balloon force with a neural network for detecting multiple phases