arXiv:1705.05582 · Physical review. B./Physical review. B

Machine learning of explicit order parameters: From the Ising model to SU(2) lattice gauge theory

Sebastian J. Wetzel, Manuel Scherzer

Published Nov 8, 2017• 137 citations

Abstract

We present a solution to the problem of interpreting neural networks classifying phases of matter. We devise a procedure for reconstructing the decision function of an artificial neural network as a simple function of the input, provided the decision function is sufficiently symmetric. In this case one can easily deduce the quantity by which the neural network classifies the input. The method is applied to the Ising model and SU(2) lattice gauge theory. In both systems we deduce the explicit expressions of the order parameters from the decision functions of the neural networks. We assume no prior knowledge about the Hamiltonian or the order parameters except Monte Carlo--sampled configurations.

DOI: 10.1103/physrevb.96.184410

Related papers

Kernel methods for interpretable machine learning of order parameters

Pedro Ponte, Roger G. Melko

Machine learning is capable of discriminating phases of matter, and finding associated phase transitions, directly from large data sets of raw state configurations. In the context of condensed matter physics, most progress in the field of supervised learning has come from employing neural networks as classifiers. Although very powerful, such algorithms suffer from a lack of interpretability, which is usually desired in scientific applications in order to associate learned features with physical phenomena. In this paper, we explore support vector machines (SVMs), which are a class of supervised kernel methods that provide interpretable decision functions. We find that SVMs can learn the mathematical form of physical discriminators, such as order parameters and Hamiltonian constraints, for a set of two-dimensional spin models: the ferromagnetic Ising model, a conserved-order-parameter Ising model, and the Ising gauge theory. The ability of SVMs to provide interpretable classification highlights their potential for automating feature detection in both synthetic and experimental data sets for condensed matter and other many-body systems.

arXiv:1704.05848Physical review. B./Physical review. BNov 27, 2017136 citations

Exploring Phase Diagrams with Functional Renormalization and Artificial Neural Networks: From the Hubbard Model to Lattice Gauge Theory

Sebastian J. Wetzel

This thesis is dedicated to provide physicists with new and improved techniques to \nexamine phase diagrams and phase transitions. \nOne the one hand, an analysis of the effects of different regularization schemes in \nfunctional renormalization group calculations is provided. Building on this knowledge, \nan investigation of the phase diagram of the Hubbard-Model on the square \nlattice is performed using the functional renormalization group. The calculation \nreveals leading instabilities in the d-wave superconducting and different antiferromagnetic \nchannels. In the symmetry broken phases there are a changing Fermi \nsurface geometry, coexistence phases of d-wave superconductivity and antiferromagnetism \nas well as a mutual tendency of superconductivity and antiferromagnetism \nto repel each other. \nOn the other hand, a scheme to discover phase transitions using unsupervised \nartifcial neural networks is developed. Further, a method to interpret artifcial \nneural networks is introduced. These methods are applied to systems ranging from \nthe two dimensional Ising Model to four dimensional SU(2) lattice gauge theory. \nThey find the existence of different phases, calculate phase boundaries and derive \nthe explicit formulas of the quantities by which the neural network distinguishes \nbetween phases. It turns out that these quantities are order parameters and other \nthermodynamic quantities.

Jan 1, 20180 citations

Randomized-Gauge Test for Machine Learning of Ising Model Order Parameter

Tomoyuki Morishita, Synge Todo

Recently, machine learning has been applied successfully for identifying phases and phase transitions of the Ising models. The continuous phase transition is characterized by spontaneous symmetry breaking, which can not be detected in general from a single spin configuration. To investigate if neural networks can extract correlations among spin snapshots, we propose a new test using the random-gauge Ising model. We show that neural networks can extract the order parameter or the energy of the random-gauge model as in the ferromagnetic case. We also discuss how and where the information of random gauge is encoded in neural networks and attempt to reconstruct the gauge from the neural network parameters. We find that the fully connected network encodes the effect of random gauge to its weights naturally. In contrast, the convolutional network copes with the randomness by assigning different network parts to local gauge patterns. This observation indicates that although the latter demonstrates higher performance than the former for the present randomized-gauge test, the former is more effective and suitable for dealing with models with spatial randomness.

arXiv:2109.05533Journal of the Physical Society of JapanMar 2, 20221 citation

Parameter diagnostics of phases and phase transition learning by neural networks

Philippe Suchsland, Stefan Weßel

We present 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. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate 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. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

arXiv:1802.09876Physical review. B./Physical review. BMay 31, 201878 citations

Machine Learning as a universal tool for quantitative investigations of phase transitions

Cinzia Giannetti, Biagio Lucini A, Davide Vadacchino

The problem of identifying the phase of a given system for a certain value of the temperature can be reformulated as a classification problem in Machine Learning. Taking as a prototype the Ising model and using the Support Vector Machine as a tool to classify Monte Carlo generated configurations, we show that the critical region of the system can be clearly identified and the symmetry that drives the transition can be reconstructed from the performance of the learning process. The role of the discrete symmetry of the system in obtaining this result is discussed. A finite size analysis of the learned Support Vector Machine decision function allows us to determine the critical temperature and critical exponents with a precision that is comparable to that of the most efficient numerical approaches relying on a known Hamiltonian description of the system. For the determination of the critical temperature and of the critical exponent connected with the divergence of the correlation length, other than the availability of a range of temperatures having information on both phases, the method we propose does not rest on any physical input on the system, and in particular is agnostic to its Hamiltonian, its symmetry properties and its order parameter. Hence, our investigation provides a first significant step in the direction of devising robust tools for quantitative analyses of phase transitions in cases in which an order parameter is not known.

arXiv:1812.06726Nuclear Physics BMay 16, 201951 citations

Unsupervised identification of topological phase transitions using predictive models

Eliška Greplová, Agnes Valenti, Gregor Boschung +3 more

Machine-learning driven models have proven to be powerful tools for the identification of phases of matter. In particular, unsupervised methods hold the promise to help discover new phases of matter without the need for any prior theoretical knowledge. While for phases characterized by a broken symmetry, the use of unsupervised methods has proven to be successful, topological phases without a local order parameter seem to be much harder to identify without supervision. Here, we use an unsupervised approach to identify boundaries of the topological phases. We train artificial neural nets to relate configurational data or measurement outcomes to quantities like temperature or tuning parameters in the Hamiltonian. The accuracy of these predictive models can then serve as an indicator for phase transitions. We successfully illustrate this approach on both the classical Ising gauge theory as well as on the quantum ground state of a generalized toric code.

Apr 7, 202051 citations