Machine learning via relativity-inspired quantum dynamics

TL;DR

This paper introduces a relativistic quantum dynamics-based machine learning scheme using a quantum detector in a cavity, demonstrating enhanced accuracy and expressivity in the relativistic regime through simulation and kernel-machine theory.

Contribution

It proposes a novel relativistic quantum machine learning framework and shows its advantages over classical regimes via simulation and theoretical analysis.

Findings

Significant accuracy improvement in the relativistic regime.

Enhanced expressivity of the quantum system in the relativistic regime.

Potential for implementation in circuit QED platforms.

Abstract

We present a machine-learning scheme based on the relativistic dynamics of a quantum system, namely a quantum detector inside a cavity resonator. An equivalent analog model can be realized for example in a circuit QED platform subject to properly modulated driving fields. We consider a reservoir-computing scheme where the input data are embedded in the modulation of the system (equivalent to the acceleration of the relativistic object) and the output data are obtained by linear combinations of measured observables. As an illustrative example, we have simulated such a relativistic quantum machine for a challenging classification task, showing a very large enhancement of the accuracy in the relativistic regime. Using kernel-machine theory, we show that in the relativistic regime the task-independent expressivity is dramatically magnified with respect to the Newtonian regime.