Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.11131 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915855032385536 |
|---|---|
| author | Delhibabu, Radhakrishnan |
| author_facet | Delhibabu, Radhakrishnan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_11131 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Barren Plateaus: A Scalable Quantum Convolutional Architecture for High-Fidelity Image Classification Delhibabu, Radhakrishnan Machine Learning 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. |
| title | Beyond Barren Plateaus: A Scalable Quantum Convolutional Architecture for High-Fidelity Image Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.11131 |