Complexity Powered Machine Intelligent Classification of Quantum Many-Body Dynamics

TL;DR

This paper introduces a complexity-boosted distance measure for machine learning that effectively classifies quantum many-body phases from time series data without prior knowledge, even in noisy or disordered conditions.

Contribution

The authors develop a novel complexity-based distance metric that enhances unsupervised learning of quantum phases from dynamic data, improving classification accuracy in challenging scenarios.

Findings

Improved unsupervised classification of quantum phases.

Effective in noisy and disordered environments.

Applicable to various quantum models like time crystals and Aubry-André.

Abstract

Identifying and classifying quantum phases from measurable time series in many-body dynamics have significant values, yet face formidable challenges, requiring profound knowledge of physicists. Here, to achieve a pure data-driven machine intelligent classification, we introduce a complexity boosted distance measure that captures the inherent complexity of dynamic evolution series in different quantum many-body phases. Significantly, the introduction of complexity-boosted distance leads to remarkable improvements of unsupervised manifold learning of quantum many-body dynamics, which are exemplified in discrete time crystal model, Aubry-Andr\'e model, and quantum east model. Our method does not require any prior knowledge and exhibits effectiveness even in imperfect, disordered, and noisy situations that are challenging for human scientists. Successful classification of dynamic phases in many-body systems holds the potential to enable crucial applications, including identification of tsunamis, earthquakes, catastrophes and future trends in finance.