Unsupervised learning of phase transitions via modified anomaly detection with autoencoders

Abstract

In this paper, a modified method of anomaly detection using convolutional autoencoders is employed to predict phase transitions in several statistical mechanical models on a square lattice. We show that, when the autoencoder is trained with input data of various phases, the mean-square-error loss function can serve as a measure of disorder, and its standard deviation becomes an excellent indicator of critical points. We find that various types of phase transition points, including first-order, second-order, and topological ones, can be faithfully detected by the peaks in the standard deviation of the loss function. Besides, the values of transition points can be accurately determined under the analysis of finite-size scaling. Our results demonstrate that the present approach has general application in identification/classification of phase transitions even without a priori knowledge of the systems in question.

9 pages, 8 figures

References in corpus (18)

• Learning phase transitions by confusion
• Ground state fidelity from tensor network representations
• Unsupervised machine learning of topological phase transitions from experimental data
• New ordered phases in a class of generalized XY models
• Unsupervised learning of topological phase transitions using Calinski-Harabaz index
• Competing nematic interactions in a generalized XY model in two and three dimensions
• Phase diagram study of a two-dimensional frustrated antiferromagnet via unsupervised machine learning
• Machine-learning detection of the Berezinskii-Kosterlitz-Thouless transitions in the q-state clock models
• Accurate simulation of q-state clock model
• Monte Carlo study of duality and the Berezinskii-Kosterlitz-Thouless phase transitions of the two-dimensional $q$-state clock model in flow representations
• Finite-size analysis in neural network classification of critical phenomena
• Neural Network flows of low q-state Potts and clock Models
• Hybrid Berezinskii-Kosterlitz-Thouless and Ising topological phase transition in the generalized two-dimensional XY model using tensor networks
• Unsupervised mapping of phase diagrams of 2D systems from infinite projected entangled-pair states via deep anomaly detection
• Deep Learning of Phase Transitions for Quantum Spin Chains from Correlation Aspects
• Robust Identification of Topological Phase Transition by Self-Supervised Machine Learning Approach
• Berezinskii-Kosterlitz-Thouless transition from Neural Network Flows
• Self-Supervised Ensemble Learning: A Universal Method for Phase Transition Classification of Many-Body Systems

Cited by in corpus (5)

• Phase determination with and without deep learning
• Unsupervised Machine Learning Phase Classification for Falicov-Kimball Model
• A Unsupervised Framework for Identifying Diverse Quantum Phase Transitions Using Classical Shadow Tomography
• Uncovering Magnetic Phases with Synthetic Data and Physics-Informed Training
• Identifying phase transitions in physical systems with neural networks: a neural architecture search perspective