A neural network replaces Gaussian process regression in dynamical scaling analysis, cutting computational cost while improving accuracy on 2D Ising and Potts models.
In the dynamical scaling analy- sis of second-order transitions, the relaxation timeτ(T) exhibits a characteristic critical behavior, and the data must be transformed accordingly
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.stat-mech 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Dynamical scaling method improved by a deep learning approach
A neural network replaces Gaussian process regression in dynamical scaling analysis, cutting computational cost while improving accuracy on 2D Ising and Potts models.