VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning
This addresses scalability and noise resilience problems for quantum machine learning practitioners, representing a novel hybrid approach rather than an incremental improvement.
The paper tackles challenges in variational quantum circuits (VQCs) for quantum machine learning by proposing VQC-MLPNet, a hybrid quantum-classical architecture where a VQC generates first-layer weights for a classical multilayer perceptron during training, with inference performed classically. The result demonstrates exponential improvements in representation capacity relative to quantum circuit depth and qubit count, achieving high accuracy and robustness on diverse datasets while using significantly fewer trainable parameters.
Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience. We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically. This design preserves scalability, reduces quantum resource demands, and enables practical deployment. We provide a theoretical analysis based on statistical learning and neural tangent kernel theory, establishing explicit risk bounds and demonstrating improved expressivity and trainability compared to purely quantum or existing hybrid approaches. These theoretical insights demonstrate exponential improvements in representation capacity relative to quantum circuit depth and the number of qubits, providing clear computational advantages over standalone quantum circuits and existing hybrid quantum architectures. Empirical results on diverse datasets, including quantum-dot classification and genomic sequence analysis, show that VQC-MLPNet achieves high accuracy and robustness under realistic noise models, outperforming classical and quantum baselines while using significantly fewer trainable parameters.