Discovering Phase Transitions with Unsupervised Learning
This work addresses the challenge of phase discovery in physics using machine learning, offering a novel application but is incremental in combining existing unsupervised methods with known physical models.
The paper tackled the problem of identifying phases and phase transitions in many-body systems, such as the Ising model, by applying unsupervised learning techniques like principal component analysis and clustering to raw spin configurations, successfully extracting physical indicators like order parameters and structure factors.
Unsupervised learning is a discipline of machine learning which aims at discovering patterns in big data sets or classifying the data into several categories without being trained explicitly. We show that unsupervised learning techniques can be readily used to identify phases and phases transitions of many body systems. Starting with raw spin configurations of a prototypical Ising model, we use principal component analysis to extract relevant low dimensional representations the original data and use clustering analysis to identify distinct phases in the feature space. This approach successfully finds out physical concepts such as order parameter and structure factor to be indicators of the phase transition. We discuss future prospects of discovering more complex phases and phase transitions using unsupervised learning techniques.