Improving Quantum Machine Learning via Heat-Bath Algorithmic Cooling

TL;DR

This paper introduces a thermodynamics-inspired quantum cooling method to improve sampling efficiency in quantum machine learning, reducing computational overhead and enhancing performance on noisy quantum devices.

Contribution

It develops a heat-bath algorithmic cooling protocol for QML, avoiding complex quantum algorithms and improving sample efficiency through entropy management.

Findings

Enhanced sample efficiency in QML training and prediction

Reduced computational overhead for score and gradient estimation

Compatible with noisy intermediate-scale quantum devices

Abstract

This work introduces an approach rooted in quantum thermodynamics to enhance sampling efficiency in quantum machine learning (QML). We propose conceptualizing quantum supervised learning as a thermodynamic cooling process. Building on this concept, we develop a quantum refrigerator protocol that enhances sample efficiency during training and prediction without the need for Grover iterations or quantum phase estimation. Inspired by heat-bath algorithmic cooling protocols, our method alternates entropy compression and thermalization steps to decrease the entropy of qubits, increasing polarization towards the dominant bias. This technique minimizes the computational overhead associated with estimating classification scores and gradients, presenting a practical and efficient solution for QML algorithms compatible with noisy intermediate-scale quantum devices.