Beyond Barren Plateaus: A Scalable Quantum Convolutional Architecture for High-Fidelity Image Classification
This addresses a critical bottleneck for researchers and practitioners in quantum machine learning, enabling scalable quantum computer vision with high fidelity, though it is incremental in advancing existing QCNN paradigms.
The paper tackled the problem of barren plateaus and poor accuracy in Quantum Convolutional Neural Networks (QCNNs) by proposing a novel architecture with localized cost functions and tensor-network initialization, achieving 98.7% accuracy on MNIST, a significant improvement over the 52.32% baseline.
While Quantum Convolutional Neural Networks (QCNNs) offer a theoretical paradigm for quantum machine learning, their practical implementation is severely bottlenecked by barren plateaus -- the exponential vanishing of gradients -- and poor empirical accuracy compared to classical counterparts. In this work, we propose a novel QCNN architecture utilizing localized cost functions and a hardware-efficient tensor-network initialization strategy to provably mitigate barren plateaus. We evaluate our scalable QCNN on the MNIST dataset, demonstrating a significant performance leap. By resolving the gradient vanishing issue, our optimized QCNN achieves a classification accuracy of 98.7\%, a substantial improvement over the baseline QCNN accuracy of 52.32\% found in unmitigated models. Furthermore, we provide empirical evidence of a parameter-efficiency advantage, requiring $\mathcal{O}(\log N)$ fewer trainable parameters than equivalent classical CNNs to achieve $>95\%$ convergence. This work bridges the gap between theoretical quantum utility and practical application, providing a scalable framework for quantum computer vision tasks without succumbing to loss landscape concentration.