Identifying Topological Phase Transitions in Experiments Using Manifold Learning

TL;DR

This paper introduces a machine learning approach using Diffusion Maps to identify and classify topological phase transitions in experimental data, even with limited data and without edge state information.

Contribution

It applies Diffusion Maps to experimental optical data to detect topological phase transitions, demonstrating effectiveness with partial and edge-free data.

Findings

Successfully identified topological phase transitions from limited experimental data.

Method works without requiring edge state information.

Effective in analyzing data from a small part of the system.

Abstract

We demonstrate the identification and classification of topological phase transitions from experimental data using Diffusion Maps: a nonlocal unsupervised machine learning method. We analyze experimental data from an optical system undergoing a topological phase transition and demonstrate the ability of this approach to identify topological phase transitions even when the data originates from a small part of the system, and does not even include edge states.