Unsupervised machine learning of topological phase transitions from experimental data

Abstract

Identifying phase transitions is one of the key challenges in quantum many-body physics. Recently, machine learning methods have been shown to be an alternative way of localising phase boundaries also from noisy and imperfect data and without the knowledge of the order parameter. Here we apply different unsupervised machine learning techniques including anomaly detection and influence functions to experimental data from ultracold atoms. In this way we obtain the topological phase diagram of the Haldane model in a completely unbiased fashion. We show that the methods can successfully be applied to experimental data at finite temperature and to data of Floquet systems, when postprocessing the data to a single micromotion phase. Our work provides a benchmark for unsupervised detection of new exotic phases in complex many-body systems.

arXiv comment19 pages, 12 figures

References in corpus (87)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Auto-Encoding Variational Bayes
• The NumPy array: a structure for efficient numerical computation
• Photonic Floquet Topological Insulators
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Experimental realisation of the topological Haldane model
• Artificial gauge potentials for neutral atoms
• Machine learning phases of matter
• Photovoltaic Hall effect in graphene
• Tutorial on Variational Autoencoders
• Understanding Black-box Predictions via Influence Functions
• Universal High-Frequency Behavior of Periodically Driven Systems: from Dynamical Stabilization to Floquet Engineering
• Topological characterization of periodically-driven quantum systems
• Atomic quantum gases in periodically driven optical lattices
• Measuring the Chern number of Hofstadter bands with ultracold bosonic atoms
• Topological Bands for Ultracold Atoms
• Many-body quantum state tomography with neural networks
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Floquet topological insulators
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Experimental reconstruction of the Berry curvature in a topological Bloch band
• Discovering physical concepts with neural networks
• Observation of a dynamical topological phase transition
• Machine learning quantum phases of matter beyond the fermion sign problem
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Reinforcement Learning in Different Phases of Quantum Control
• Machine Learning Topological States
• Identifying topological order through unsupervised machine learning
• Quantum Loop Topography for Machine Learning
• Machine Learning Topological Invariants with Neural Networks
• An Aharonov-Bohm interferometer for determining Bloch band topology
• Machine Learning Phases of Strongly Correlated Fermions
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Fast machine-learning online optimization of ultra-cold-atom experiments
• Seeing topological order in time-of-flight measurements
• Mapping the Berry Curvature from Semiclassical Dynamics in Optical Lattices
• Measuring topology by dynamics: Chern number from linking number
• Machine learning vortices at the Kosterlitz-Thouless transition
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Unsupervised machine learning and band topology
• Measuring quantized circular dichroism in ultracold topological matter
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Machine Learning for Quantum Matter
• Integrating Neural Networks with a Quantum Simulator for State Reconstruction
• Kernel methods for interpretable machine learning of order parameters
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• Tomography of band insulators from quench dynamics
• Deep Learning the Quantum Phase Transitions in Random Two-Dimensional Electron Systems
• Extracting the Chern number from the dynamics of a Fermi gas: Implementing a quantum Hall bar for cold atoms
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Probing topology by "heating": Quantized circular dichroism in ultracold atoms
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Unsupervised phase discovery with deep anomaly detection
• Unsupervised Manifold Clustering of Topological Phononics
• Topological quantum phase transitions retrieved through unsupervised machine learning
• Improved detection of small atom numbers through image processing
• Multiparameter optimisation of a magneto-optical trap using deep learning
• Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2
• Machine Learning Assisted Insight to Spin Ice Dy${}_2$Ti${}_2$O${}_7$
• Neural network quantum state tomography in a two-qubit experiment
• Unsupervised machine learning of topological phase transitions from experimental data
• Probing hidden spin order with interpretable machine learning
• Unsupervised identification of topological order using predictive models
• Real space mapping of topological invariants using artificial neural networks
• Discovering Symmetry Invariants and Conserved Quantities by Interpreting Siamese Neural Networks
• Machine Learning for Achieving Bose-Einstein Condensation of Thulium Atoms
• Unsupervised machine learning of quantum phase transitions using diffusion maps
• Correlator Convolutional Neural Networks: An Interpretable Architecture for Image-like Quantum Matter Data
• Quantum phase recognition via unsupervised machine learning
• Automated discovery of characteristic features of phase transitions in many-body localization
• Machine learning topological phases in real space
• Interpreting machine learning of topological quantum phase transitions
• Visualizing Strange Metallic Correlations in the 2D Fermi-Hubbard Model with AI
• Linear Response Theory and Optical Conductivity of Floquet Topological Insulators
• Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
• Quantum topology identification with deep neural networks and quantum walks
• Phase Detection with Neural Networks: Interpreting the Black Box
• Loading Ultracold Gases in Topological Floquet Bands: Current and Center-of-Mass Responses
• Self-organizing maps as a method for detecting phase transitions and phase identification
• Deep data mining in a real space: Separation of intertwined electronic responses in a lightly-doped BaFe2As2
• Optical lattice experiments at unobserved conditions and scales through generative adversarial deep learning
• Characterizing the phase diagram of finite-size dipolar Bose-Hubbard systems
• Exploring phases of the Su-Schrieffer-Heeger model with tSNE

Cited by in corpus (49)

• Artificial Intelligence and Machine Learning for Quantum Technologies
• Unsupervised machine learning of topological phase transitions from experimental data
• Machine learning discovery of new phases in programmable quantum simulator snapshots
• Variational Quantum Anomaly Detection: Unsupervised mapping of phase diagrams on a physical quantum computer
• Unsupervised and supervised learning of interacting topological phases from single-particle correlation functions
• An unsupervised deep learning algorithm for single-site reconstruction in quantum gas microscopes
• Interpretable and unsupervised phase classification
• 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 learning of topological phase diagram using topological data analysis
• Replacing neural networks by optimal analytical predictors for the detection of phase transitions
• Experimental demonstration of adversarial examples in learning topological phases
• Learning minimal representations of stochastic processes with variational autoencoders
• The percolating cluster is invisible to image recognition with deep learning
• Unsupervised mapping of phase diagrams of 2D systems from infinite projected entangled-pair states via deep anomaly detection
• Unsupervised learning of phase transitions via modified anomaly detection with autoencoders
• Detection of Berezinskii-Kosterlitz-Thouless transition via Generative Adversarial Networks
• Hamiltonian learning with real-space impurity tomography in topological moire superconductors
• Learning the Fuzzy Phases of Small Photonic Condensates
• Observing a topological phase transition with deep neural networks from experimental images of ultracold atoms
• Vortex detection in atomic Bose-Einstein condensates using neural networks trained on synthetic images
• High-dimensional reinforcement learning for optimization and control of ultracold quantum gases
• Error-tolerant quantum convolutional neural networks for symmetry-protected topological phases
• Unveiling quantum phase transitions from traps in variational quantum algorithms
• Prediction of the morphological evolution of a splashing drop using an encoder-decoder
• Unsupervised Learning of Rydberg Atom Array Phase Diagram with Siamese Neural Networks
• Identifying topology of leaky photonic lattices with machine learning
• Deep Learning of Phase Transitions for Quantum Spin Chains from Correlation Aspects
• Characterizing out-of-distribution generalization of neural networks: application to the disordered Su-Schrieffer-Heeger model
• Extracting Off-Diagonal Order from Diagonal Basis Measurements
• Detecting the phase transition in a strongly-interacting Fermi gas by unsupervised machine learning
• Machine learning classification of two-dimensional vortex configurations
• Quaternion-based machine learning on topological quantum systems
• Berezinskii-Kosterlitz-Thouless transition from Neural Network Flows
• Machine learning the Ising transition: A comparison between discriminative and generative approaches
• Learning interactions between Rydberg atoms
• Self-Supervised Ensemble Learning: A Universal Method for Phase Transition Classification of Many-Body Systems
• Renormalization-group-inspired neural networks for computing topological invariants
• Deep Neural Network-assisted improvement of quantum compressed sensing tomography
• Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments
• Classifying topological neural network quantum states via diffusion maps
• Exploring phases of the Su-Schrieffer-Heeger model with tSNE
• On the capacity of a quantum perceptron for storing biased patterns
• Learning quantum symmetries with interactive quantum-classical variational algorithms
• Connecting Topological Anderson and Mott Insulators in Disordered Interacting Fermionic Systems
• Exploring exotic configurations with anomalous features using deep learning: Application of classical and quantum-classical hybrid anomaly detection
• A Unsupervised Framework for Identifying Diverse Quantum Phase Transitions Using Classical Shadow Tomography
• Unsupervised classification of disordered patterns in an oppositely charged colloidal system
• Transfer learning of many-body electronic correlation entropy from local measurements