Selecting relevant structural features for glassy dynamics by information imbalance

We numerically investigate the identification of relevant structural features that contribute to the dynamical heterogeneity in a model glass-forming liquid. By employing the recently proposed information imbalance technique, we select these features from a range of physically motivated descriptors. This selection process is performed in a supervised manner (using both dynamical and structural data) and an unsupervised manner (using only structural data). We then apply the selected features to predict future dynamics using a machine learning technique. One of the advantages of the information imbalance technique is that it does not assume any model a priori, i.e., it is a non-parametric method. Finally, we discuss the potential applications of this approach in identifying the dominant mechanisms governing the glassy slow dynamics.