Learning Langevin dynamics with QCD phase transition

TL;DR

This paper employs deep CNNs to classify QCD phase transition types and estimate dynamical parameters from stochastic field configurations, demonstrating robustness even with noise.

Contribution

It introduces a novel approach using CNNs on image-like spectra to recognize phase transition order and extract parameters in Langevin dynamics of QCD.

Findings

CNNs accurately classify phase transition types

The method reliably reconstructs damping coefficients

Recognition performance is unaffected by noise

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 $1+1$-dimensional Langevin equation for $\sigma$ field. The well-trained CNNs accurately classify the first-order phase transition and crossover from $\sigma$ 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 $\eta$ from the intricate field configurations.