Machine learning for classifying the chiral phase transition in AdS/QCD

AdS/QCD is a phenomenological application of the gauge/gravity duality to strongly-interacting nuclear matter, including the quark-gluon plasma (QGP). This work uses machine learning to classify the order of the chiral phase transition between ordinary nuclear matter and the QGP. Our machine learning method is a supervised-learning synthesis of four standard classification algorithms: classification and regression trees (CART), k-Nearest Neighbors (kNN), Support Vector Machines (SVM) with a linear kernel, and Random Forest (RF). It is trained on a subset of data with known behavior, and tested on the remaining data, with a 100% success rate. We also discuss the application of this machine learning method to the development of an AdS/QCD model featuring a critical point in the QCD phase diagram, which aligns with the current experimental program at Brookhaven National Laboratory.