Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system

Abstract

Still under debate is the question of whether machine learning is capable of going beyond black-box modeling for complex physical systems. We investigate the generalizing and interpretability properties of learning algorithms. To this end, we use supervised and unsupervised learning to infer the phase boundaries of the active Ising model, starting from an ensemble of configurations of the system. We illustrate that unsupervised learning techniques are powerful at identifying the phase boundaries in the control parameter space, even in situations of phase coexistence. It is demonstrated that supervised learning with neural networks is capable of learning the characteristics of the phase diagram, such that the knowledge obtained at a limited set of control variables can be used to determine the phase boundaries across the phase diagram. In this way, we show that properly designed supervised learning provides predictive power to regions in the phase diagram that are not included in the training phase of the algorithm. We stress the importance of introducing interpretability methods in order to perform a physically relevant classification of the phases with deep learning.

References in corpus (36)

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Novel type of phase transition in a system of self-driven particles
• Collective motion
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Collective motion of self-propelled particles interacting without cohesion
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Quantum Entanglement in Neural Network States
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Machine Learning Topological Invariants with Neural Networks
• Machine Learning Phases of Strongly Correlated Fermions
• Self-Learning Monte Carlo Method
• Accelerate Monte Carlo Simulations with Restricted Boltzmann Machines
• Equivalence of restricted Boltzmann machines and tensor network states
• From Phase to Micro-Phase Separation in Flocking Models: The Essential Role of Non-Equilibrium Fluctuations
• Mutual Information, Neural Networks and the Renormalization Group
• Revisiting the flocking transition using active spins
• Machine learning vortices at the Kosterlitz-Thouless transition
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Neural Network Renormalization Group
• Latent Space Purification via Neural Density Operators
• Machine learning out-of-equilibrium phases of matter
• Kernel methods for interpretable machine learning of order parameters
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Flocking with discrete symmetry: the 2d Active Ising Model
• Self-Learning Monte Carlo Method in Fermion Systems
• Parameter diagnostics of phases and phase transition learning by neural networks
• Scale-invariant Feature Extraction of Neural Network and Renormalization Group Flow
• Learning phase transitions from dynamics
• Smallest Neural Network to Learn the Ising Criticality
• Can Boltzmann Machines Discover Cluster Updates ?
• Deep neural networks for direct, featureless learning through observation: the case of 2d spin models

Cited by in corpus (28)

• Explainable Machine Learning for Scientific Insights and Discoveries
• Machine Learning for Quantum Matter
• Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
• Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Machine learning discovery of new phases in programmable quantum simulator snapshots
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Extending machine learning classification capabilities with histogram reweighting
• Unsupervised learning using topological data augmentation
• Interpretable and unsupervised phase classification
• Accurate phonon blockade detector composed of a quadratically coupled optomechanical system
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Unsupervised Learning Eigenstate Phases of Matter
• Optical lattice experiments at unobserved conditions and scales through generative adversarial deep learning
• Detecting composite orders in layered models via machine learning
• From predicting to learning dissipation from pair correlations of active liquids
• Machine Learning Phase Transition: An Iterative Proposal
• Quantifying dissipation in flocking dynamics: When tracking internal states matters
• Unsupervised Machine Learning of Quenched Gauge Symmetries: A Proof-of-Concept Demonstration
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• Variational Autoencoder Analysis of Ising Model Statistical Distributions and Phase Transitions
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• Conservation Laws and Spin System Modeling through Principal Component Analysis
• Global exploration of phase behavior in frustrated Ising models using unsupervised learning techniques
• Dreaming up scale invariance via inverse renormalization group
• Predicting parameters of a model cuprate superconductor using machine learning