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

  title={Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination.},
  author={Wenjian Hu and Rajiv R. P. Singh and Richard T. Scalettar},
  journal={Physical review. E},
  volume={95 6-1},
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-1 Ising (BSI) model, and the two-dimensional XY model-and we examine critically what machine learning is teaching us. We find that quantified principal components from PCA not only allow… 

Quantitative and interpretable order parameters for phase transitions from persistent homology

Modern methods in computational topology are applied to the task of discovering and characterizing phase transitions, using persistent homology, which computes the births and deaths of individual topological features as a coarse-graining scale or sublevel threshold is increased, to summarize multiscale and high-point correlations in a spin configuration.

Identifying topological order through unsupervised machine learning

An unsupervised machine learning algorithm that identifies topological order is demonstrated and is shown to be capable of classifying samples of the two-dimensional XY model by winding number and capture the Berezinskii–Kosterlitz–Thouless transition.

Unsupervised identification of the phase transition on the 2D-Ising model

We investigate deep learning autoencoders for the unsupervised recognition of phase transitions in physical systems formulated on a lattice. We use spin configurations produced for the 2-dimensional

Machine learning of frustrated classical spin models (II): Kernel principal component analysis

In this work, we apply a principal component analysis (PCA) method with a kernel trick to study the classification of phases and phase transitions in classical XY models of frustrated lattices.

Machine learning of frustrated classical spin models (II): Kernel principal component analysis

In this work, we apply a principal component analysis (PCA) method with a kernel trick to study the classification of phases and phase transitions in classical XY models of frustrated lattices.

Confusion scheme in machine learning detects double phase transitions and quasi-long-range order.

This study uses the confusion scheme of the unsupervised learning and investigates critical behavior of various systems which exhibit single (double) phase transitions with (without) quasi- long-range order to conclude that regardless of the presence of a quasi-long-range Order, single and double phase transitions can be detected via the confusion schemes.

Unsupervised machine learning account of magnetic transitions in the Hubbard model.

We employ several unsupervised machine learning techniques, including autoencoders, random trees embedding, and t-distributed stochastic neighboring ensemble (t-SNE), to reduce the dimensionality of,

Unsupervised machine learning for detection of phase transitions in off-lattice systems. I. Foundations.

It is demonstrated that PCA autonomously discovers order-parameter-like quantities that report on phase transitions, mitigating the need for a priori construction or identification of a suitable order parameter-thus streamlining the routine analysis of phase behavior.

Parameter diagnostics of phases and phase transition learning by neural networks

An analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer, and demonstrates how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks.

Unsupervised learning of topological phase transitions using the Calinski-Harabaz index

This paper proposes to use the Calinski-Harabaz index, defined roughly as the ratio $\bar D/\bar \sigma$, to determine the critical points, at which thech index reaches a maximum or minimum value, or jump sharply, in several statistical models, including ones that contain a BKT phase transition.



Learning phase transitions by confusion

This work proposes a neural-network approach to finding phase transitions, based on the performance of a neural network after it is trained with data that are deliberately labelled incorrectly, and paves the way to the development of a generic tool for identifying unexplored phase transitions.

Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders

  • S. Wetzel
  • Computer Science
    Physical review. E
  • 2017
Unsupervised machine learning techniques to learn features that best describe configurations of the two-dimensional Ising model and the three-dimensional XY model are examined, finding that the most promising algorithms are principal component analysis and variational autoencoders.

Discovering phase transitions with unsupervised learning

This work shows that unsupervised learning techniques can be readily used to identify phases and phases transitions of many-body systems by using principal component analysis to extract relevant low-dimensional representations of the original data and clustering analysis to identify distinct phases in the feature space.

Machine learning phases of matter

It is shown that modern machine learning architectures, such as fully connected and convolutional neural networks, can identify phases and phase transitions in a variety of condensed-matter Hamiltonians.

Machine Learning Phases of Strongly Correlated Fermions

This work shows that a three dimensional convolutional network trained on auxiliary field configurations produced by quantum Monte Carlo simulations of the Hubbard model can correctly predict the magnetic phase diagram of the model at the average density of one (half filling).

Dynamics of rough surfaces generated by two-dimensional lattice spin models.

An analysis of mapped surfaces obtained from configurations of two classical statistical-mechanical spin models in the square lattice: the q -state Potts model and the spin-1 Blume-Capel model, using the Monte Carlo method and a mapping of the spin configurations to a solid-on-solid growth model.

First-order phase transition and tricritical scaling behavior of the Blume-Capel model: A Wang-Landau sampling approach.

The authors' estimation of the tricritical eigenvalue exponents provides the first Wang-Landau verification of the conjectured exact values, demonstrating the effectiveness of the density-of-states-based approach in finite-size scaling study of multicritical phenomena.

Entanglement in a simple quantum phase transition

What entanglement is present in naturally occurring physical systems at thermal equilibrium? Most such systems are intractable and it is desirable to study simple but realistic systems that can be

Machine learning quantum phases of matter beyond the fermion sign problem

It is demonstrated that convolutional neural networks (CNN) can be optimized for quantum many-fermion systems such that they correctly identify and locate quantum phase transitions in such systems.

Ising‐Model Spin Correlations on the Triangular Lattice

A Pfaffian representation, of the partition function of the triangular lattice is used to derive expressions for various two, four, and six spin correlations in terms of Pfaffians. The pair