Rapid detection of phase transitions from Monte Carlo samples before equilibrium
arXiv:2206.13137 · doi:10.21468/SciPostPhys.13.3.057
Abstract
We found that Bidirectional LSTM and Transformer can classify different phases of condensed matter models and determine the phase transition points by learning features in the Monte Carlo raw data before equilibrium. Our method can significantly reduce the time and computational resources required for probing phase transitions as compared to the conventional Monte Carlo simulation. We also provide evidence that the method is robust and the performance of the deep learning model is insensitive to the type of input data (we tested spin configurations of classical models and green functions of a quantum model), and it also performs well in detecting Kosterlitz-Thouless phase transitions.
arXiv comment23 pages, 10 figures
References in corpus (15)
- Efficient Estimation of Word Representations in Vector Space
- Machine learning and the physical sciences
- Recurrent Neural Network Regularization
- Machine learning phases of matter
- word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method
- Discovering Phase Transitions with Unsupervised Learning
- Machine learning quantum phases of matter beyond the fermion sign problem
- Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
- Universal quantum criticality in the metal-insulator transition of two-dimensional interacting Dirac electrons
- Machine learning vortices at the Kosterlitz-Thouless transition
- Unsupervised machine learning account of magnetic transitions in the Hubbard model
- Machine Learning for Quantum Matter
- Unsupervised Learning of Frustrated Classical Spin Models I: Principle Component Analysis
- Unsupervised phase discovery with deep anomaly detection
- Novel Approach to Unveil Quantum Phase Transitions Using Fidelity Map