Learning Langevin dynamics with QCD phase transition
arXiv:2108.03987 · doi:10.1051/epjconf/202225910017
Abstract
In this proceeding, the deep Convolutional Neural Networks (CNNs) are deployed to recognize the order of QCD phase transition and predict the dynamical parameters in Langevin processes. To overcome the intrinsic randomness existed in a stochastic process, we treat the final spectra as image-type inputs which preserve sufficient spatiotemporal correlations. As a practical example, we demonstrate this paradigm for the scalar condensation in QCD matter near the critical point, in which the order parameter of chiral phase transition can be characterized in a -dimensional Langevin equation for field. The well-trained CNNs accurately classify the first-order phase transition and crossover from field configurations with fluctuations, in which the noise does not impair the performance of the recognition. In reconstructing the dynamics, we demonstrate it is robust to extract the damping coefficients from the intricate field configurations.
arXiv commentContribution to: SQM2021
References in corpus (14)
- Machine learning and the physical sciences
- Nonperturbative Heavy-Quark Diffusion in the Quark-Gluon Plasma
- Equivariant flow-based sampling for lattice gauge theory
- Real time evolution of non-Gaussian cumulants in the QCD critical regime
- Nonequilibrium chiral fluid dynamics including dissipation and noise
- Regressive and generative neural networks for scalar field theory
- Hydrodynamics Near a Chiral Critical Point
- Topology-Dependent Brownian Gyromotion of a Single Skyrmion
- Identifying the nature of the QCD transition in relativistic collision of heavy nuclei with deep learning
- Deep learning stochastic processes with QCD phase transition
- Towards Novel Insights in Lattice Field Theory with Explainable Machine Learning
- Little-Bang and Femto-Nova in Nucleus-Nucleus Collisions
- Chiral Phase Transition at Finite Temperature in the Linear Sigma Model
- Dynamical fluctuations in critical regime and across the 1st order phase transition