Unlearnable phases of matter

TL;DR

This paper demonstrates that certain complex phases of matter are computationally hard to learn using machine learning, introducing new diagnostics like conditional mutual information to identify these phases.

Contribution

It reveals fundamental limitations in machine learning for identifying mixed-state phases of matter and proposes CMI as a diagnostic tool for phase complexity.

Findings

Long-range CMI indicates locally indistinguishable states.

Hard-to-learn phases include symmetry-breaking phases.

CMI can diagnose phase transitions and error thresholds.

Abstract

We identify fundamental limitations in machine learning by demonstrating that non-trivial mixed-state phases of matter are computationally hard to learn. Focusing on unsupervised learning of distributions, we show that autoregressive neural networks fail to learn global properties of distributions characterized by locally indistinguishable (LI) states. We demonstrate that conditional mutual information (CMI) is a useful diagnostic for LI: we show that for classical distributions, long-range CMI of a state implies a spatially LI partner. By introducing a restricted statistical query model, we prove that nontrivial phases with long-range CMI, such as strong-to-weak spontaneous symmetry breaking phases, are hard to learn. We validate our claims by using recurrent, convolutional, and Transformer neural networks to learn the syndrome and physical distributions of toric/surface code under bit flip noise. Our findings suggest hardness of learning as a diagnostic tool for detecting mixed-state phases and transitions and error-correction thresholds, and they suggest CMI and more generally ``non-local Gibbsness'' as metrics for how hard a distribution is to learn.