We demonstrate that supervised machine learning (ML) with entanglement spectrum can give useful information for constructing phase diagram in the half-filled one-dimensional extended Hubbard model. Combining ML with infinite-size density-matrix renormalization group, we confirm that bond-order-wave phase remains stable in the thermodynamic limit.
@article{arxiv.1904.06032,
title = {Machine Learning Phase Diagram in the Half-filled One-dimensional Extended Hubbard Model},
author = {Kazuya Shinjo and Kakeru Sasaki and Satoru Hase and Shigetoshi Sota and Satoshi Ejima and Seiji Yunoki and Takami Tohyama},
journal= {arXiv preprint arXiv:1904.06032},
year = {2019}
}