Improving Quantum Machine Learning via Heat-Bath Algorithmic Cooling
This work addresses sampling inefficiency in quantum machine learning, offering a practical solution for noisy intermediate-scale quantum devices, though it appears incremental as it builds on existing heat-bath algorithmic cooling protocols.
The authors tackled the problem of sampling inefficiency in quantum machine learning by conceptualizing quantum supervised learning as a thermodynamic cooling process, resulting in a quantum refrigerator protocol that enhances sample efficiency during training and prediction without requiring Grover iterations or quantum phase estimation.
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.