Fragmentation is Efficiently Learnable by Quantum Neural Networks

TL;DR

This paper introduces a quantum machine learning task called fragment classification, which is efficiently solvable by quantum computers but remains classically hard, highlighting a potential quantum advantage.

Contribution

It formalizes the fragment classification problem in quantum systems and proves its quantum efficiency while showing classical intractability under certain conditions.

Findings

Quantum algorithms can classify quantum state fragments efficiently.

Classical dequantization techniques fail for this problem.

Provides evidence of a quantum advantage in a physically motivated task.

Abstract

In certain classes of physical quantum systems, the exponentially large state space "fragments" into many low-dimensional, dynamically disconnected subspaces. We introduce a learning problem known as fragment classification, where given a quantum state input, one is interested in classifying to which subspace the state belongs. We prove that solving this learning problem is efficient on a quantum computer when the fragmentation phenomenon satisfies certain conditions. Furthermore, we give evidence supporting the classical hardness of this task by demonstrating that known dequantization techniques fail for the fragment classification problem. Consequently, this work provides a rare example of a physically motivated quantum machine learning task that is both efficient for quantum computers to perform and admits no known classical dequantization.