TY  - JOUR
PB  - SciPost Foundation
DO  - 10.21468/SciPostPhys.13.3.057
TI  - Rapid detection of phase transitions from Monte Carlo samples before equilibrium
PY  - 2022/09/09
UR  - https://scipost.org/SciPostPhys.13.3.057
JF  - SciPost Physics
JA  - SciPost Phys.
VL  - 13
IS  - 3
SP  - 057
A1  - Ding, Jiewei
AU  - Tang, Ho-Kin
AU  - Yu, Wing Chi
AB  - 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.
ER  -

@Article{10.21468/SciPostPhys.13.3.057,
	title={{Rapid detection of phase transitions from Monte Carlo samples before equilibrium}},
	author={Jiewei Ding and Ho-Kin Tang and Wing Chi Yu},
	journal={SciPost Phys.},
	volume={13},
	pages={057},
	year={2022},
	publisher={SciPost},
	doi={10.21468/SciPostPhys.13.3.057},
	url={https://scipost.org/10.21468/SciPostPhys.13.3.057},
}