Identifying Quantum Phase Transitions with Adversarial Neural Networks

Abstract

The identification of phases of matter is a challenging task, especially in quantum mechanics, where the complexity of the ground state appears to grow exponentially with the size of the system. We address this problem with state-of-the-art deep learning techniques: adversarial domain adaptation. We derive the phase diagram of the whole parameter space starting from a fixed and known subspace using unsupervised learning. The input data set contains both labeled and unlabeled data instances. The first kind is a system that admits an accurate analytical or numerical solution, and one can recover its phase diagram. The second type is the physical system with an unknown phase diagram. Adversarial domain adaptation uses both types of data to create invariant feature extracting layers in a deep learning architecture. Once these layers are trained, we can attach an unsupervised learner to the network to find phase transitions. We show the success of this technique by applying it on several paradigmatic models: the Ising model with different temperatures, the Bose-Hubbard model, and the SSH model with disorder. The input is the ground state without any manual feature engineering, and the dimension of the parameter space is unrestricted. The method finds unknown transitions successfully and predicts transition points in close agreement with standard methods. This study opens the door to the classification of physical systems where the phases boundaries are complex such as the many-body localization problem or the Bose glass phase.

10 pages, 8 figures, computational appendix is available at https://github.com/PatrickHuembeli/Adversarial-Domain-Adaptation-for-Identifying-Phase-Transitions

References in corpus (12)

• Many body localization and thermalization in quantum statistical mechanics
• Learning phase transitions by confusion
• Topological Anderson Insulator
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Restricted-Boltzmann-Machine Learning for Solving Strongly Correlated Quantum Systems
• Unsupervised Generative Modeling Using Matrix Product States
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• Solving the Bose-Hubbard model with machine learning
• Machine learning technique to find quantum many-body ground states of bosons on a lattice
• Quantum phase recognition via unsupervised machine learning
• First-order phase transition in a 2D random-field Ising model with conflicting dynamics

Cited by in corpus (77)

• Machine learning and the physical sciences
• Transfer learning in hybrid classical-quantum neural networks
• Identifying topological order through unsupervised machine learning
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Unsupervised machine learning and band topology
• Machine Learning for Quantum Matter
• Quantum Adversarial Machine Learning
• Unsupervised phase discovery with deep anomaly detection
• Topological quantum phase transitions retrieved through unsupervised machine learning
• Unveiling phase transitions with machine learning
• Machine Learning for Condensed Matter Physics
• Unsupervised machine learning of topological phase transitions from experimental data
• Phase diagram of disordered higher-order topological insulator: A machine learning study
• Self-learning Monte Carlo with Deep Neural Networks
• Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• Smallest Neural Network to Learn the Ising Criticality
• Automated discovery of characteristic features of phase transitions in many-body localization
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Machine learning topological phases in real space
• Machine learning discovery of new phases in programmable quantum simulator snapshots
• Quantitative and Interpretable Order Parameters for Phase Transitions from Persistent Homology
• Mapping distinct phase transitions to a neural network
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Divergence of predictive model output as indication of phase transitions
• Learning Quantum Hamiltonians from Single-qubit Measurements
• Machine learning topological invariants of non-Hermitian systems
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Model-Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
• Topological Persistence Machine of Phase Transitions
• Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
• Unsupervised and supervised learning of interacting topological phases from single-particle correlation functions
• Unsupervised learning using topological data augmentation
• Phase Detection with Neural Networks: Interpreting the Black Box
• Interpretable and unsupervised phase classification
• Visualizing Quantum Phases And Identifying Quantum Phase Transitions By Nonlinear Dimensionality Reduction
• Hessian-based toolbox for reliable and interpretable machine learning in physics
• Transfer learning of phase transitions in percolation and directed percolation
• Transforming Generalized Ising Model into Boltzmann Machine
• A learning by confusion approach to characterize phase transitions
• Statistical Complexity of Quantum Learning
• Mapping out phase diagrams with generative classifiers
• Random matrix analysis of deep neural network weight matrices
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Unsupervised Learning Eigenstate Phases of Matter
• Anomalous topological edge modes in a periodically-driven trimer lattice
• Neural networks in quantum many-body physics: a hands-on tutorial
• Unsupervised mapping of phase diagrams of 2D systems from infinite projected entangled-pair states via deep anomaly detection
• Machine Learning of Nonequilibrium Phase Transition in an Ising Model on Square Lattice
• Certificates of quantum many-body properties assisted by machine learning
• Study of phase transition of Potts model with Domain Adversarial Neural Network
• Phase diagram reconstruction of the Bose-Hubbard model with a Restricted Boltzmann Machine wavefunction
• Quantum Reservoir Computing for Speckle-Disorder Potentials
• Exponentially improved efficient machine learning for quantum many-body states with provable guarantees
• Probing Criticality in Quantum Spin Chains with Neural Networks
• Machine Learning the Square-Lattice Ising Model
• Adversarial Machine Learning Phases of Matter
• Unveiling quantum phase transitions from traps in variational quantum algorithms
• Detecting composite orders in layered models via machine learning
• Phase determination with and without deep learning
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• Emergence of a finite-size-scaling function in the supervised learning of the Ising phase transition
• Unsupervised interpretable learning of topological indices invariant under permutations of atomic bands
• A simple framework for contrastive learning phases of matter
• Learning by Confusion: The Phase Diagram of the Holstein Model
• Machine learning of mirror skin effects in the presence of disorder
• MATGANIP: Learning to Discover the Structure-Property Relationship in Perovskites with Generative Adversarial Networks
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• A sampling-guided unsupervised learning method to capture percolation in complex networks
• Machine Learning Percolation Model
• Machine learning classification of two-dimensional vortex configurations
• Boundary between noise and information applied to filtering neural network weight matrices
• Learning phases with Quantum Monte Carlo simulation cell
• Supervised learning of an interacting 2D hard-core boson model of a weak topological insulator using correlation functions
• Interpretable Phase Detection and Classification with Persistent Homology
• Developing a Maximum-Entropy Restricted Boltzmann Machine with a Quantum Thermodynamics Formalism
• Interpretable representation learning of quantum data enabled by probabilistic variational autoencoders