Replacing neural networks by optimal analytical predictors for the detection of phase transitions

Abstract

Identifying phase transitions and classifying phases of matter is central to understanding the properties and behavior of a broad range of material systems. In recent years, machine-learning (ML) techniques have been successfully applied to perform such tasks in a data-driven manner. However, the success of this approach notwithstanding, we still lack a clear understanding of ML methods for detecting phase transitions, particularly of those that utilize neural networks (NNs). In this work, we derive analytical expressions for the optimal output of three widely used NN-based methods for detecting phase transitions. These optimal predictions correspond to the results obtained in the limit of high model capacity. Therefore, in practice they can, for example, be recovered using sufficiently large, well-trained NNs. The inner workings of the considered methods are revealed through the explicit dependence of the optimal output on the input data. By evaluating the analytical expressions, we can identify phase transitions directly from experimentally accessible data without training NNs, which makes this procedure favorable in terms of computation time. Our theoretical results are supported by extensive numerical simulations covering, e.g., topological, quantum, and many-body localization phase transitions. We expect similar analyses to provide a deeper understanding of other classification tasks in condensed matter physics.

arXiv comment19+20 pages, 8+12 figures; improved presentation and numerical implementation, added discussion on model capacity and data set size

References in corpus (83)

• Unpaired Majorana fermions in quantum wires
• Cold bosonic atoms in optical lattices
• New directions in the pursuit of Majorana fermions in solid state systems
• Probing many-body dynamics on a 51-atom quantum simulator
• Machine learning and the physical sciences
• Barren plateaus in quantum neural network training landscapes
• The many-body localization phase transition
• Machine learning phases of matter
• Predicting Many Properties of a Quantum System from Very Few Measurements
• Quantum Phases of Matter on a 256-Atom Programmable Quantum Simulator
• Quantum Simulation of Antiferromagnetic Spin Chains in an Optical Lattice
• Probing Topological Spin Liquids on a Programmable Quantum Simulator
• Learning phase transitions by confusion
• Programmable quantum simulation of 2D antiferromagnets with hundreds of Rydberg atoms
• Many-body localization: an introduction and selected topics
• Discovering Phase Transitions with Unsupervised Learning
• Quantum Simulators: Architectures and Opportunities
• Quantum advantage in learning from experiments
• Probing entanglement in a many-body-localized system
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• QuSpin: a Python Package for Dynamics and Exact Diagonalisation of Quantum Many Body Systems part I: spin chains
• Machine learning quantum phases of matter beyond the fermion sign problem
• QuSpin: a Python Package for Dynamics and Exact Diagonalisation of Quantum Many Body Systems. Part II: bosons, fermions and higher spins
• Reconstructing quantum states with generative models
• Spin transport in a tunable Heisenberg model realized with ultracold atoms
• Simulating quantum many-body dynamics on a current digital quantum computer
• Identifying topological order through unsupervised machine learning
• Quantum Loop Topography for Machine Learning
• Observation of measurement-induced quantum phases in a trapped-ion quantum computer
• Machine Learning Topological Invariants with Neural Networks
• Machine Learning Phases of Strongly Correlated Fermions
• An introduction to integrable techniques for one-dimensional quantum systems
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• Quantum critical behavior at the many-body-localization transition
• Critical Properties of the Many-Body Localization Transition
• Machine learning vortices at the Kosterlitz-Thouless transition
• Entanglement and topological entropy of the toric code at finite temperature
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Unsupervised machine learning and band topology
• Exact ground states and topological order in interacting Kitaev/Majorana chains
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Machine Learning for Quantum Matter
• Probing many-body localization with neural networks
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Machine learning out-of-equilibrium phases of matter
• Kernel methods for interpretable machine learning of order parameters
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Parallel Quantum Simulation of Large Systems on Small Quantum Computers
• Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Unsupervised phase discovery with deep anomaly detection
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Restricted Boltzmann Machines for Quantum States with Nonabelian or Anyonic Symmetries
• Unsupervised machine learning of topological phase transitions from experimental data
• Finite-size scaling method for the Berezinskii-Kosterlitz-Thouless transition
• Probing hidden spin order with interpretable machine learning
• Transverse spin dynamics in the anisotropic Heisenberg model realized with ultracold atoms
• Deep Learning the Quantum Phase Transitions in Random Electron Systems: Applications to Three Dimensions
• Unsupervised identification of topological order using predictive models
• Learning the ground state of a non-stoquastic quantum Hamiltonian in a rugged neural network landscape
• Learning multiple order parameters with interpretable machines
• Learning phase transitions from dynamics
• Automated discovery of characteristic features of phase transitions in many-body localization
• Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
• Interpreting machine learning of topological quantum phase transitions
• One-Component Order Parameter in URu${}_2$Si${}_2$ Uncovered by Resonant Ultrasound Spectroscopy and Machine Learning
• Divergence of predictive model output as indication of phase transitions
• Interpretable Machine Learning Study of Many-Body Localization Transition in Disordered Quantum Ising Spin Chains
• Essential finite-size effect in the 2D XY model
• Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system
• Direct Evidence of the Discontinuous Character of the Kosterlitz-Thouless Jump
• Analyzing non-equilibrium quantum states through snapshots with artificial neural networks
• Phase Detection with Neural Networks: Interpreting the Black Box
• Interpretable and unsupervised phase classification
• Supervised machine learning of ultracold atoms with speckle disorder
• Correlation-Enhanced Neural Networks as Interpretable Variational Quantum States
• Machine learning of phase transitions in nonlinear polariton lattices
• Identification of hidden order and emergent constraints in frustrated magnets using tensorial kernel methods
• Detecting ergodic bubbles at the crossover to many-body localization using neural networks
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Unsupervised mapping of phase diagrams of 2D systems from infinite projected entangled-pair states via deep anomaly detection
• A learning algorithm with emergent scaling behavior for classifying phase transitions

Cited by in corpus (4)

• A learning by confusion approach to characterize phase transitions
• Learning phase transitions from regression uncertainty: A new regression-based machine learning approach for automated detection of phases of matter
• Efficient and quantum-adaptive machine learning with fermion neural networks
• Snake net and balloon force with a neural network for detecting multiple phases