Discovering Phase Transitions with Unsupervised Learning

TL;DR

This paper demonstrates how unsupervised learning methods like PCA and clustering can identify phases and phase transitions in many-body systems, exemplified by the Ising model, without prior labeling.

Contribution

It introduces a novel approach applying unsupervised learning to detect phases and transitions directly from raw data in physical systems.

Findings

Successfully identified phases in the Ising model

Extracted physical indicators like order parameter

Demonstrated potential for complex phase discovery

Abstract

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.