A no free lunch theorem for untrained quantum circuits in machine learning

TL;DR

This paper establishes that untrained quantum circuits do not offer a theoretical advantage in machine learning, challenging claims of their effectiveness without empirical validation.

Contribution

It proves a no free lunch theorem for untrained quantum circuits, showing their average performance is no better than classical alternatives.

Findings

Untrained quantum circuits have negligible average advantage.

Theoretical results cast doubt on using untrained quantum circuits in ML.

Empirical validation is necessary for claims of quantum advantage.

Abstract

This paper proves that if an untrained quantum circuit is used as a resource in a machine learning workflow, then on average no quantum circuit is better than any other that can achieve the same set of computational effects. This is the titular no free lunch theorem. The paper also proves a supporting theorem that even if the idealisations of the no free lunch theorem are omitted, the average quantum advantage remains negligible at best. These results cast serious doubt on several proposals to use untrained quantum circuits in machine learning workflows: at best such claims should be substantiated empirically, as this paper proves there is no a priori theoretical reason to suppose that introducing an untrained quantum circuit will increase performance.