Quantum Surrogate-Driven Image Classifier: A Gradient-Free Approach to Avoid Barren Plateaus

2025/05/08 by Xie, Yichen
#FOS: Physical sciences #Quantum Physics (quant-ph)

paper · doi:10.48550/arxiv.2505.05249

Abstract

Training deep quantum neural networks (QNNs) for image classification is notoriously difficult due to vanishing gradients (barren plateaus) and limited nonlinearity in purely unitary circuits. We propose a novel gradient-free surrogate-driven framework combined with mid-circuit measurement and reset of ancillary qubits to induce effective nonunitarity. Our approach uses a classical neural surrogate to predict measurement outcomes from circuit parameters to avoid direct gradients. Theoretical results prove that bypassing quantum gradients mitigates plateau issues. Experiments on MNIST, CIFAR-10, and CIFAR-100 with 15-qubit, 6-layer circuits using four resettable ancillas demonstrate superior accuracy compared to direct-gradient QNNs and classical baselines. Our method also serves as a potential for a generalized training framework applicable to various QNN architectures beyond image classification.

Citations

• Qubit-reuse compilation with mid-circuit measurement and reset
• Quantum embeddings for machine learning
• Quantum Computing in the NISQ era and beyond

Cited by

• Layered KIK quantum error mitigation for dynamic circuits and error correction

Related

• Efficient Quantum Convolutional Neural Networks for Image Classification: Overcoming Hardware Constraints
• Quanvolutional Neural Networks: Powering Image Recognition with Quantum Circuits
• Quantum Deep Learning: Sampling Neural Nets with a Quantum Annealer
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits
• Classification of NEQR Processed Classical Images using Quantum Neural Networks (QNN)