Chin. Phys. Lett.  2020, Vol. 37 Issue (8): 080501    DOI: 10.1088/0256-307X/37/8/080501
 GENERAL |
Machine Learning for Many-Body Localization Transition
Wen-Jia Rao*
School of Science, Hangzhou Dianzi University, Hangzhou 310027, China
Wen-Jia Rao 2020 Chin. Phys. Lett. 37 080501
 Download: PDF(770KB)   PDF(mobile)(752KB)   HTML Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract We employ the methods of machine learning to study the many-body localization (MBL) transition in a 1D random spin system. By using the raw energy spectrum without pre-processing as training data, it is shown that the MBL transition point is correctly predicted by the machine. The structure of the neural network reveals the nature of this dynamical phase transition that involves all energy levels, while the bandwidth of the spectrum and nearest level spacing are the two dominant patterns and the latter stands out to classify phases. We further use a comparative unsupervised learning method, i.e., principal component analysis, to confirm these results.
Received: 10 May 2020      Published: 28 July 2020
 PACS: 05.30.Rt (Quantum phase transitions) 75.10.Pq (Spin chain models) 89.20.Ff (Computer science and technology) 05.70.Jk (Critical point phenomena)
Fund: Supported by the National Natural Science Foundation of China (Grant Nos. 11904069 and 11847005).
 TRENDMD: URL: http://cpl.iphy.ac.cn/10.1088/0256-307X/37/8/080501       OR      http://cpl.iphy.ac.cn/Y2020/V37/I8/080501
 [1] Hui Zhou, Zhao-Kai Li, Heng-Yan Wang, Hong-Wei Chen, Xin-Hua Peng, Jiang-Feng Du. Experimental Observation of the Ground-State Geometric Phase of Three-Spin $XY$ Model[J]. Chin. Phys. Lett., 2016, 33(06): 080501 [2] WANG Bo, HUANG Hai-Lin, SUN Zhao-Yu, KOU Su-Peng. Quantum Fidelity and Thermal Phase Transitions in a Two-Dimensional Spin System[J]. Chin. Phys. Lett., 2012, 29(12): 080501