No Reference-Free Generalization in Quantum Machine Learning

2026-06-21

AI Summary

This work addresses the challenge that existing quantum machine learning models struggle to assign discriminative semantics to quantum states lying outside the directions covered by training data when no external quantum reference frame is available. The authors propose a reference-frame-independent supervised learning framework that enforces classifiers to preserve all unitary symmetries unbroken by the training set, thereby revealing fundamental limits on generalization. Their theoretical analysis demonstrates that Hilbert space dimensionality alone is insufficient for learnability; instead, physical structure—such as symmetry properties, measurement bases, and locality—constitutes the essential resource for endowing unseen quantum states with meaningful semantics. They further prove that when the training states do not span the full Hilbert space, all pure states orthogonal to their span must yield identical predictions, and they quantify the exponentially diverse set of training directions required for universal concept learning.

Abstract

Quantum machine learning is often motivated by the exponentially large state space of quantum systems, but this promise leaves a basic generalization problem unresolved: how can a learner assign different meanings to unseen quantum directions when the training data provide no preferred basis, measurement frame, or other orienting structure? We address this identifiability problem by formulating supervised learning without an external quantum reference frame, so that predictions cannot depend on an arbitrary choice of Hilbert-space coordinates. This requirement forces the learned classifier to preserve every unitary symmetry left unbroken by the training data. We prove that whenever the training states fail to span the full Hilbert space, all pure states orthogonal to their span must receive the same prediction -- even when those states are mutually orthogonal and perfectly distinguishable once an appropriate measurement is supplied. The limitation is therefore not caused by state discrimination, optimization, or computational power, but by missing reference information. We further establish a robust version under weak symmetry breaking and show that learning generic unstructured concepts on multiqubit systems requires exponentially many independently oriented training directions. Numerical illustrations visualize the resulting prediction collapse and its controlled relaxation. Our results identify feature maps, measurement bases, Hamiltonians, locality, symmetry priors, architectures, and sufficiently diverse training states as operational resources for generalization. The central implication is that Hilbert-space dimension alone is not a learnable feature space: successful QML must specify the physical structure that gives unseen quantum directions semantic meaning.

Problem

• quantum machine learning
• generalization
• reference frame
• identifiability
• symmetry

Innovation

• quantum reference frame
• generalization
• unitary symmetry
• Hilbert space identifiability
• quantum machine learning