Detection of Berezinskii-Kosterlitz-Thouless transition via Generative Adversarial Networks
arXiv:2110.05383 · doi:10.21468/SciPostPhys.12.3.107
Abstract
The detection of phase transitions in quantum many-body systems with lowest possible prior knowledge of their details is among the most rousing goals of the flourishing application of machine-learning techniques to physical questions. Here, we train a Generative Adversarial Network (GAN) with the Entanglement Spectrum of a system bipartition, as extracted by means of Matrix Product States ansätze. We are able to identify gapless-to-gapped phase transitions in different one-dimensional models by looking at the machine inability to reconstruct outsider data with respect to the training set. We foresee that GAN-based methods will become instrumental in anomaly detection schemes applied to the determination of phase-diagrams.
arXiv comment14 pages, 5 figures
References in corpus (36)
- Many-Body Physics with Ultracold Gases
- The density-matrix renormalization group in the age of matrix product states
- Entanglement Entropy and Quantum Field Theory
- Machine learning and the physical sciences
- Ultracold atomic gases in optical lattices: mimicking condensed matter physics and beyond
- Entanglement Spectrum as a Generalization of Entanglement Entropy: Identification of Topological Order in Non-Abelian Fractional Quantum Hall Effect States
- Machine learning phases of matter
- Entanglement spectrum of a topological phase in one dimension
- Learning phase transitions by confusion
- Discovering Phase Transitions with Unsupervised Learning
- Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders
- Discovering Phases, Phase Transitions and Crossovers through Unsupervised Machine Learning: A critical examination
- Identifying topological order through unsupervised machine learning
- An introduction to integrable techniques for one-dimensional quantum systems
- Mutual Information, Neural Networks and the Renormalization Group
- One-Dimensional Magnetism
- Machine Learning for Quantum Matter
- The Tensor Networks Anthology: Simulation techniques for many-body quantum lattice systems
- Unsupervised phase discovery with deep anomaly detection
- Counterflow and paired superfluidity in one-dimensional Bose mixtures in optical lattices
- Scaling of the entanglement spectrum near quantum phase transitions
- Unsupervised machine learning of topological phase transitions from experimental data
- Machine-Learning Studies on Spin Models
- Quantum droplets of bosonic mixtures in a one-dimensional optical lattice
- Automated discovery of characteristic features of phase transitions in many-body localization
- Unsupervised learning universal critical behavior via the intrinsic dimension
- Superfluid density and quasi-long-range order in the one-dimensional disordered Bose-Hubbard model
- Density-Matrix Renormalization Group Study of Extended Kitaev-Heisenberg Model
- Machine-learning detection of the Berezinskii-Kosterlitz-Thouless transitions in the q-state clock models
- Intrinsic dimension of path integrals: data mining quantum criticality and emergent simplicity
- Generative models for sampling and phase transition indication in spin systems
- A machine learning approach to the Berezinskii-Kosterlitz-Thouless transition in classical and quantum models
- Collisionless drag for a one-dimensional two-component Bose-Hubbard model
- Pairing and pair superfluid density in one-dimensional Hubbard models
- Unsupervised mapping of phase diagrams of 2D systems from infinite projected entangled-pair states via deep anomaly detection
- Beresinskii-Kosterlitz-Thouless transition within the sine-Gordon approach: the role of the vortex-core energy
Cited by in corpus (4)
- Exploring QCD matter in extreme conditions with Machine Learning
- Phase Diagram Detection via Gaussian Fitting of Number Probability Distribution
- Deep Learning of Phase Transitions for Quantum Spin Chains from Correlation Aspects
- Fluctuation based interpretable analysis scheme for quantum many-body snapshots