Phase determination with and without deep learning

Abstract

Detection of phase transitions is a critical task in statistical physics, traditionally pursued through analytic methods and direct numerical simulations. Recently, machine-learning techniques have emerged as promising tools in this context, with a particular focus on supervised and unsupervised learning methods, along with non-learning approaches. In this work, we study the performance of unsupervised learning in detecting phase transitions in the $J_1$-$J_2$ Ising model on the square lattice. The model is chosen due to its simplicity and complexity, thus providing an understanding of the application of machine-learning techniques in both straightforward and challenging scenarios. We propose a simple method based on a direct comparison of configurations. The reconstruction error, defined as the mean-squared distance between two configurations, is used to determine the critical temperatures ($T_c$). The results from the comparison of configurations are contrasted with that of the configurations generated by variational autoencoders. Our findings highlight that for certain systems, a simpler method can yield results comparable to more complex neural networks. This work contributes to the broader understanding of machine-learning applications in statistical physics and introduces an efficient approach to the detection of phase transitions using machine determination techniques.

arXiv comment17 pages, 12 figures

References in corpus (54)

• Machine learning and the physical sciences
• Machine learning phases of matter
• A high-bias, low-variance introduction to Machine Learning for physicists
• Discovering Phase Transitions with Unsupervised Learning
• Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
• Machine Learning Phases of Strongly Correlated Fermions
• Detection of phase transition via convolutional neural network
• Machine Learning of Explicit Order Parameters: From the Ising Model to SU(2) Lattice Gauge Theory
• Ashkin-Teller criticality and pseudo first-order behavior in a frustrated Ising model on the square lattice
• Identifying Quantum Phase Transitions with Adversarial Neural Networks
• Phase transitions in the frustrated Ising model on the square lattice
• Machine learning of phase transitions in the percolation and XY models
• Unsupervised phase discovery with deep anomaly detection
• Machine learning of quantum phase transitions
• Unveiling phase transitions with machine learning
• Parameter diagnostics of phases and phase transition learning by neural networks
• Machine-Learning Studies on Spin Models
• Phase diagram of the Ising square lattice with competing interactions
• Monte Carlo studies of the square Ising model with next-nearest-neighbor interactions
• Super-resolving the Ising model with convolutional neural networks
• Location of the Potts-critical end point in the frustrated Ising model on the square lattice
• Analysis of the phase transition for the Ising model on the frustrated square lattice
• The critical temperature of the 2D-Ising model through Deep Learning Autoencoders
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Learning the Ising Model with Generative Neural Networks
• Deep Learning on the 2-Dimensional Ising Model to Extract the Crossover Region with a Variational Autoencoder
• Supervised and unsupervised learning of directed percolation
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
• Exploring neural network training strategies to determine phase transitions in frustrated magnetic models
• Tensor network simulation for the frustrated $J_1$-$J_2$ Ising model on the square lattice
• Phase transitions in a frustrated Ising antiferromagnet on a square lattice
• Extracting Critical Exponent by Finite-Size Scaling with Convolutional Neural Networks
• Interpretable and unsupervised phase classification
• Metastable states in the J1-J2 Ising model
• Identifying structural changes with unsupervised machine learning methods
• Finite-size analysis in neural network classification of critical phenomena
• Neural Network flows of low q-state Potts and clock Models
• Dimensionless ratios: characteristics of quantum liquids and their phase transitions
• Weak first-order phase transitions in the frustrated square lattice J1-J2 classical Ising model
• Hilbert Space Fragmentation and Ashkin-Teller Criticality in Fluctuation Coupled Ising Models
• Can a CNN trained on the Ising model detect the phase transition of the $q$-state Potts model?
• Overlap Distribution of the Three-Dimensional Ising Model
• Phase transition of Frustrated Ising model via D-wave Quantum Annealing Machine
• Machine Learning Phase Diagram in the Half-filled One-dimensional Extended Hubbard Model
• The percolating cluster is invisible to image recognition with deep learning
• Unsupervised learning of phase transitions via modified anomaly detection with autoencoders
• Machine Learning of Nonequilibrium Phase Transition in an Ising Model on Square Lattice
• Detecting composite orders in layered models via machine learning
• Machine Learning the Square-Lattice Ising Model
• Non-monotonic behavior of the Binder Parameter in the discrete spin systems
• Minimalist Neural Networks training for phase classification in diluted-Ising models
• Machine learning the 2D percolation model
• Free energy and metastable states in the square-lattice $J_1$-$J_2$ Ising model

Cited by in corpus (2)

• Comments on the minimal training set for CNN: a case study of the frustrated $J_1$-$J_2$ Ising model on the square lattice
• Learning phase transitions by siamese neural network