Unsupervised learning universal critical behavior via the intrinsic dimension

Abstract

The identification of universal properties from minimally processed data sets is one goal of machine learning techniques applied to statistical physics. Here, we study how the minimum number of variables needed to accurately describe the important features of a data set - the intrinsic dimension ($I_d$) - behaves in the vicinity of phase transitions. We employ state-of-the-art nearest neighbors-based $I_d$-estimators to compute the $I_d$ of raw Monte Carlo thermal configurations across different phase transitions: first-, second-order and Berezinskii-Kosterlitz-Thouless. For all the considered cases, we find that the $I_d$ uniquely characterizes the transition regime. The finite-size analysis of the $I_d$ allows not just to identify critical points with an accuracy comparable with methods that rely on {\it a priori} identification of order parameters, but also to determine the corresponding (critical) exponent $\nu$ in case of continuous transitions. For the case of topological transitions, this analysis overcomes the reported limitations affecting other unsupervised learning methods. Our work reveals how raw data sets display unique signatures of universal behavior in the absence of any dimensional reduction scheme, and suggest direct parallelism between conventional order parameters in real space, and the intrinsic dimension in the data space.

References in corpus (34)

• Machine learning and the physical sciences
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• Machine learning phases of matter
• A high-bias, low-variance introduction to Machine Learning for physicists
• Learning phase transitions by confusion
• Discovering Phase Transitions with Unsupervised Learning
• Computational Studies of Quantum Spin Systems
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Quantum Entanglement in Neural Network States
• Estimating the intrinsic dimension of datasets by a minimal neighborhood information
• Quantum Boltzmann Machine
• Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
• Identifying topological order through unsupervised machine learning
• Quantum Loop Topography for Machine Learning
• Machine Learning Phases of Strongly Correlated Fermions
• Quantum many-body dynamics in two dimensions with artificial neural networks
• Identifying Quantum Phase Transitions using Artificial Neural Networks on Experimental Data
• Machine learning vortices at the Kosterlitz-Thouless transition
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Unsupervised machine learning account of magnetic transitions in the Hubbard model
• Machine Learning for Quantum Matter
• Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
• Classifying Snapshots of the Doped Hubbard Model with Machine Learning
• Modelling the influence of data structure on learning in neural networks: the hidden manifold model
• Unsupervised Manifold Clustering of Topological Phononics
• Topological quantum phase transitions retrieved through unsupervised machine learning
• Finite-size scaling method for the Berezinskii-Kosterlitz-Thouless transition
• Detecting signals of weakly first-order phase transitions in two-dimensional Potts models
• Unsupervised machine learning of quantum phase transitions using diffusion maps
• Principal Component Analysis for Fermionic Critical Points
• Visualizing Strange Metallic Correlations in the 2D Fermi-Hubbard Model with AI
• Extending machine learning classification capabilities with histogram reweighting
• Intrinsic dimension estimation for locally undersampled data
• The intrinsic dimensionality of spectro-polarimetric data

Cited by in corpus (37)

• Dissipative Floquet Dynamics: from Steady State to Measurement Induced Criticality in Trapped-ion Chains
• Many-Body Localization in the Age of Classical Computing
• Measurement-induced criticality as a data-structure transition
• Dimensionality reduction of local structure in glassy binary mixtures
• Intrinsic dimension of path integrals: data mining quantum criticality and emergent simplicity
• Quantum kernels to learn the phases of quantum matter
• Quantitative analysis of phase transitions in two-dimensional XY models using persistent homology
• Learning quantum phase transitions through Topological Data Analysis
• Bilayer Hubbard model: Analysis based on the fermionic sign problem
• From observations to complexity of quantum states via unsupervised learning
• Intrinsic dimension estimation for discrete metrics
• Machine-learning detection of the Berezinskii-Kosterlitz-Thouless transition and the second-order phase transition in the XXZ models
• Wave function network description and Kolmogorov complexity of quantum many-body systems
• Estimating the Euclidean quantum propagator with deep generative modeling of Feynman paths
• Non-parametric learning critical behavior in Ising partition functions: PCA entropy and intrinsic dimension
• Data-driven discovery of statistically relevant information in quantum simulators
• Investigating Berezinskii-Kosterlitz-Thouless phase transitions in Kagome spin ice by quantifying Monte Carlo process: Distribution of Hamming distances
• Steering-induced phase transition in measurement-only quantum circuits
• Fine-tuning Neural Network Quantum States
• Detection of Berezinskii-Kosterlitz-Thouless transition via Generative Adversarial Networks
• Complexity of spin configurations dynamics due to unitary evolution and periodic projective measurements
• Exponentially improved efficient machine learning for quantum many-body states with provable guarantees
• An analysis of localization transitions using non-parametric unsupervised learning
• Network science Ising states of matter
• A learning algorithm with emergent scaling behavior for classifying phase transitions
• Probing phase transitions with correlations in configuration space
• Hamming Distance and the onset of quantum criticality
• Self-Supervised Ensemble Learning: A Universal Method for Phase Transition Classification of Many-Body Systems
• Diagnosing quantum transport from wave function snapshots
• Complexity of Quantum Trajectories
• Characterizing spin ordering via maximal row correlation in classical spin models
• Family-Vicsek universality of the binary intrinsic dimension of nonequilibrium data
• On the criticality of the configuration-space statistical geometry
• Machine-Learning Detection of the Berezinskii-Kosterlitz-Thouless Transitions
• Sampling the Liquid-Gas Critical Point with Boltzmann Generators
• Unsupervised classification of disordered patterns in an oppositely charged colloidal system
• A Unsupervised Framework for Identifying Diverse Quantum Phase Transitions Using Classical Shadow Tomography