Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination

Journal Article · · Physical Review E
 [1];  [2];  [2]
  1. Univ. of California, Davis, CA (United States). Dept. of Physics and Dept. of Computer Science; The Regents of the University of California (UC Davis)
  2. Univ. of California, Davis, CA (United States). Dept. of Physics

Here, we apply unsupervised machine learning techniques, mainly principal component analysis (PCA), to compare and contrast the phase behavior and phase transitions in several classical spin models - the square and triangular-lattice Ising models, the Blume-Capel model, a highly degenerate biquadratic-exchange spin-one Ising (BSI) model, and the 2D XY model, and examine critically what machine learning is teaching us. We find that quantified principal components from PCA not only allow exploration of different phases and symmetry-breaking, but can distinguish phase transition types and locate critical points. We show that the corresponding weight vectors have a clear physical interpretation, which is particularly interesting in the frustrated models such as the triangular antiferromagnet, where they can point to incipient orders. Unlike the other well-studied models, the properties of the BSI model are less well known. Using both PCA and conventional Monte Carlo analysis, we demonstrate that the BSI model shows an absence of phase transition and macroscopic ground-state degeneracy. The failure to capture the 'charge' correlations (vorticity) in the BSI model (XY model) from raw spin configurations points to some of the limitations of PCA. Finally, we employ a nonlinear unsupervised machine learning procedure, the 'antoencoder method', and demonstrate that it too can be trained to capture phase transitions and critical points.

Research Organization:
Univ. of California, Davis, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Basic Energy Sciences (BES) (SC-22); USDOE National Nuclear Security Administration (NNSA); National Science Foundation (NSF)
Grant/Contract Number:
NA0002908
OSTI ID:
1368102
Journal Information:
Physical Review E, Journal Name: Physical Review E Journal Issue: 6 Vol. 95; ISSN PLEEE8; ISSN 2470-0045
Publisher:
American Physical Society (APS)Copyright Statement
Country of Publication:
United States
Language:
English

References (74)

The link-prediction problem for social networks
  • Liben-Nowell, David; Kleinberg, Jon
  • Journal of the American Society for Information Science and Technology, Vol. 58, Issue 7, p. 1019-1031 https://doi.org/10.1002/asi.20591
journal January 2007
Learning To Fold Proteins Using Energy Landscape Theory journal August 2014
Monte Carlo Statistical Methods book January 2004
Auto-association by multilayer perceptrons and singular value decomposition journal September 1988
PCA Meets RG journal March 2017
On the possibility of first-order phase transitions in Ising systems of triplet ions with zero-field splitting journal May 1966
Business data mining — a machine learning perspective journal December 2001
Deep learning in neural networks: An overview journal January 2015
Scaling and Renormalization in Statistical Physics book January 2015
A quantum gas microscope for detecting single atoms in a Hubbard-regime optical lattice journal November 2009
Single-atom-resolved fluorescence imaging of an atomic Mott insulator journal August 2010
Between order and chaos journal December 2011
Single-atom imaging of fermions in a quantum-gas microscope journal July 2015
A structural approach to relaxation in glassy liquids journal February 2016
Machine learning phases of matter journal February 2017
Learning phase transitions by confusion journal February 2017
Future possibilities for artificial intelligence in the practical management of hypertension journal July 2020
Ising‐Model Spin Correlations on the Triangular Lattice. III. Isotropic Antiferromagnetic Lattice journal February 1970
Ising‐Model Spin Correlations on the Triangular Lattice journal August 1964
Drug design by machine learning: the use of inductive logic programming to model the structure-activity relationships of trimethoprim analogues binding to dihydrofolate reductase. journal December 1992
LIII. On lines and planes of closest fit to systems of points in space journal November 1901
The critical properties of the two-dimensional xy model journal March 1974
Applications of Monte Carlo methods to statistical physics journal May 1997
Entanglement entropy and quantum field theory journal June 2004
Theory of the First-Order Magnetic Phase Change in U O 2 journal January 1966
Crystal Statistics. I. A Two-Dimensional Model with an Order-Disorder Transition journal February 1944
Antiferromagnetism. The Triangular Ising Net journal July 1950
Ising model for tricritical points in ternary mixtures journal August 1974
Spin-1 lattice-gas model. I. Condensation and solidification of a simple fluid journal June 1975
Statistical Mechanics of the X Y Model. II. Spin-Correlation Functions journal February 1971
Ising Model for the λ Transition and Phase Separation in He 3 - He 4 Mixtures journal September 1971
Entanglement in a simple quantum phase transition journal September 2002
Entropy of entanglement and correlations induced by a quench: Dynamics of a quantum phase transition in the quantum Ising model journal May 2007
Phase diagrams and critical behavior in Ising square lattices with nearest- and next-nearest-neighbor interactions journal March 1980
Monte Carlo study of the fcc Blume-Capel model journal July 1980
Zinc-blende—diamond order-disorder transition in metastable crystalline ( GaAs ) 1 − x Ge 2 x alloys journal June 1983
Orderings of a stacked frustrated triangular system in three dimensions journal May 1984
Monte Carlo analysis of the two-dimensional XY model. II. Comparison with the Kosterlitz renormalization-group equations journal August 1995
Critical behavior of the spin- 3 2 Blume-Capel model in two dimensions journal May 1998
Interplay of quantum and thermal fluctuations in a frustrated magnet journal September 2003
Phase diagrams of the spin-1 Blume-Capel film with an alternating crystal field journal February 2004
Monte Carlo study of an inhomogeneous Blume-Capel model: A case study of the local density approximation journal December 2008
Learning thermodynamics with Boltzmann machines journal October 2016
Discovering phase transitions with unsupervised learning journal November 2016
Self-learning Monte Carlo method journal January 2017
Behavior of damage spreading in the two-dimensional Blume-Capel model journal April 2002
Dynamics of rough surfaces generated by two-dimensional lattice spin models journal April 2007
Numerical linked-cluster algorithms. I. Spin systems on square, triangular, and kagomé lattices journal June 2007
First-order phase transition and tricritical scaling behavior of the Blume-Capel model: A Wang-Landau sampling approach journal August 2015
Identifying polymer states by machine learning journal March 2017
Collective Monte Carlo Updating for Spin Systems journal January 1989
Density matrix formulation for quantum renormalization groups journal November 1992
Quantum Entanglement in Neural Network States journal May 2017
Colloquium : Area laws for the entanglement entropy journal February 2010
Antiferromagnetism. The Triangular Ising Net journal June 1973
Face recognition: a convolutional neural-network approach journal January 1997
Following a moving target-Monte Carlo inference for dynamic Bayesian models journal February 2001
Reducing the Dimensionality of Data with Neural Networks journal July 2006
Solving the quantum many-body problem with artificial neural networks journal February 2017
A Fast Learning Algorithm for Deep Belief Nets journal July 2006
Machine Learning for Detecting Gene-Gene Interactions: A Review journal January 2006
Deep Learning in Neural Networks: An Overview text January 2014
Single-atom imaging of fermions in a quantum-gas microscope text January 2015
First-order phase transition and tricritical scaling behavior of the Blume-Capel model: a Wang-Landau sampling approach text January 2015
Machine learning phases of matter text January 2016
Discovering Phase Transitions with Unsupervised Learning text January 2016
Learning phase transitions by confusion text January 2016
Self-Learning Monte Carlo Method text January 2016
Identifying polymer states by machine learning text January 2017
Quantum Entanglement in Neural Network States text January 2017
Interplay of quantum and thermal fluctuations in a frustrated magnet text January 2003
Phase Diagrams of the Spin-1 Blume-Capel Film With an Alternating Crystal Field text January 2003
The Critical Behaviour of the Spin-3/2 Blume-Capel Model in Two Dimensions text January 1999
Between Order and Chaos. journal January 2003

Cited By (60)

Machine learning of frustrated classical spin models (II): Kernel principal component analysis journal June 2018
Identifying topological order through unsupervised machine learning journal May 2019
Unsupervised machine learning for detection of phase transitions in off-lattice systems. I. Foundations journal November 2018
Unsupervised machine learning for detection of phase transitions in off-lattice systems. II. Applications journal November 2018
Machine learning the many-body localization transition in random spin systems journal September 2018
Machine learning & artificial intelligence in the quantum domain: a review of recent progress journal June 2018
From DFT to machine learning: recent approaches to materials science–a review journal May 2019
Machine Learning Many-Body Localization: Search for the Elusive Nonergodic Metal journal December 2018
Characterizing the phase diagram of finite-size dipolar Bose-Hubbard systems journal January 2020
Accelerating lattice quantum Monte Carlo simulations using artificial neural networks: Application to the Holstein model journal July 2019
Criticality and factorization in the Heisenberg chain with Dzyaloshinskii-Moriya interaction journal July 2019
Unsupervised learning eigenstate phases of matter journal August 2019
Self-learning Monte Carlo method: Continuous-time algorithm journal October 2017
Machine learning of explicit order parameters: From the Ising model to SU(2) lattice gauge theory journal November 2017
Principal component analysis for fermionic critical points journal November 2017
Kernel methods for interpretable machine learning of order parameters journal November 2017
Restricted Boltzmann machine learning for solving strongly correlated quantum systems journal November 2017
Machine learning Z 2 quantum spin liquids with quasiparticle statistics journal December 2017
Machine learning vortices at the Kosterlitz-Thouless transition journal January 2018
Real-space mapping of topological invariants using artificial neural networks journal March 2018
Identifying quantum phase transitions with adversarial neural networks journal April 2018
Self-learning Monte Carlo with deep neural networks journal May 2018
Deep learning topological invariants of band insulators journal August 2018
Extracting many-particle entanglement entropy from observables using supervised machine learning journal December 2018
Profile approach for recognition of three-dimensional magnetic structures journal January 2019
Self-organizing maps as a method for detecting phase transitions and phase identification journal January 2019
Probing hidden spin order with interpretable machine learning journal February 2019
Automated discovery of characteristic features of phase transitions in many-body localization journal March 2019
Machine learning of quantum phase transitions journal March 2019
Application of machine learning to two-dimensional Dzyaloshinskii-Moriya ferromagnets journal May 2019
Constructing neural stationary states for open quantum many-body systems journal June 2019
Deep learning and the AdS / CFT correspondence journal August 2018
Scale-invariant feature extraction of neural network and renormalization group flow journal May 2018
Smallest neural network to learn the Ising criticality journal August 2018
Interpretable machine learning for inferring the phase boundaries in a nonequilibrium system journal February 2019
Machine learning of phase transitions in the percolation and X Y models journal March 2019
Vector field divergence of predictive model output as indication of phase transitions journal June 2019
Deriving the order parameters of a spin-glass model using principal component analysis journal June 2019
Machine Learning Topological Invariants with Neural Networks journal February 2018
Machine Learning Detection of Bell Nonlocality in Quantum Many-Body Systems journal June 2018
Machine learning and the physical sciences journal December 2019
Flotation Height Prediction under Stable and Vibration States in Air Cushion Furnace Based on Hard Division Method journal December 2019
Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory text January 2017
Self-Learning Monte Carlo Method: Continuous-Time Algorithm text January 2017
Machine Learning Topological Invariants with Neural Networks text January 2017
Identifying Quantum Phase Transitions with Adversarial Neural Networks text January 2017
Machine learning vortices at the Kosterlitz-Thouless transition text January 2017
Self-learning Monte Carlo with Deep Neural Networks text January 2018
Real space mapping of topological invariants using artificial neural networks text January 2018
Machine Learning of Frustrated Classical Spin Models. II. Kernel Principal Component Analysis text January 2018
Machine learning of phase transitions in the percolation and XY models text January 2018
Probing hidden spin order with interpretable machine learning text January 2018
Identifying topological order through unsupervised machine learning text January 2018
Deep Learning Topological Invariants of Band Insulators text January 2018
Machine learning of quantum phase transitions text January 2018
Self-organizing maps as a method for detecting phase transitions and phase identification text January 2018
Extracting many-particle entanglement entropy from observables using supervised machine learning text January 2018
Profile approach for recognition of three-dimensional magnetic structures text January 2018
Unsupervised Learning Eigenstate Phases of Matter text January 2019
Criticality and factorization in the Heisenberg chain with Dzyaloshinskii-Moriya interaction text January 2019

Similar Records

Universal quantum operation of spin-3/2 Blume-Capel chains
Journal Article · Mon Mar 07 23:00:00 EST 2022 · Physical Review A · OSTI ID:1979611

Effects of the Random Crystal Field on the Phase Diagrams and the Magnetic Properties of a Spin-1 Blume-Capel Nanoisland
Journal Article · Sun Jul 15 00:00:00 EDT 2018 · Journal of Superconductivity and Novel Magnetism · OSTI ID:22773995

Dynamic phase transition in the kinetic spin-1 Blume-Capel model: Phase diagrams in the temperature and crystal-field interaction plane
Journal Article · Fri Jun 15 00:00:00 EDT 2007 · Journal of Experimental and Theoretical Physics · OSTI ID:21072459