Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks

• URL: http://arxiv.org/abs/2608.07822v1
• Date: Fri, 07 Aug 2026 23:50:09 GMT
• Title: Classical $\mathrm{SU}(2)$ Models Match or Exceed Shallow Variational Quantum Circuits on Vision Benchmarks
• Abstract summary: Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $mathrmSU(2)$ geometry.<n>We compare real-valued, quaternionvalued, and quantum classification heads on identical frozen features across MNIST, FashionMNIST, and CIFAR-10.<n>Our results indicate that quaternion networks provide efficient, stable alternatives to shallow VQCs on tasks lacking intrinsic quantum structure.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quaternion-valued neural networks and variational quantum circuits (VQCs) both derive local transformations from $\mathrm{SU}(2)$ geometry, yet their performance on classical supervised learning remains poorly understood. We compare real-valued, quaternion-valued, and quantum classification heads on identical frozen features across MNIST, FashionMNIST, and CIFAR-10. CIFAR-10 uses a learned 16-dimensional bottleneck and frozen ImageNet-pretrained ResNet18 features to separate architecture from representation quality. Quaternion classifiers match or approach real-valued baselines while outperforming shallow VQCs. On MNIST and FashionMNIST, quaternion networks nearly equal real-valued MLPs, whereas product-state VQCs show lower accuracy and higher cost. On CIFAR-10, quaternion networks retain 94--97% of real-valued performance and remain stable under a 32-fold increase in dimensionality. Product-state circuits underperform quaternion classifiers, while entanglement gives modest grayscale gains but reverses under pretrained CNN features (9.25 pp degradation vs.\ product-state). Fubini--Study/QFI natural gradients improve geometric alignment but not short-horizon loss reduction vs.\ Adam. A Friedman test on five-seed MNIST detects model differences ($χ^2=12.796$, $p=0.0051$, $n=5$), with Wilcoxon tests yielding large effect sizes ($d>5$) for QuatNet vs.\ quantum comparisons. For FashionMNIST and CIFAR-10, large effects ($d>2.0$) are the primary statistic given $n=3$. These results indicate that quaternion networks provide efficient, stable $\mathrm{SU}(2)$ alternatives to shallow VQCs on tasks lacking intrinsic quantum structure. Shared local $\mathrm{SU}(2)$ geometry and shallow entanglement are insufficient, within the regime studied, to confer practical quantum advantage. Conclusions are limited to shallow, measurement-limited circuits on such tasks.

Related papers

• Investigating Quantum-Embedded Transformers on Classical Datasets for Cross-Modality Classification [1.472161528588343]
  We test whether a parameterized quantum circuit (PQC) improves a hybrid quantum-classical model's performance on classical datasets.<n>Our architecture, Quantum-Embedded Attention (QEA), uses a learnable projector to compress backbone features into an $n_q$-dimensional angle vector.<n>We report all planned canonical runs, distinguish current Pauli-readout results from legacy probability-readout experiments, and analyze bottleneck, simulation, finite-shot, and noise limitations.
  arXiv  Detail & Related papers  (2026-08-07T06:09:28Z)
• Fixed-Reservoir vs Variational Quantum Architectures for Chaotic Dynamics: Benchmarking QRC and QPINN on the Lorenz System [0.14323566945483496]
  We compare two quantum approaches for chaotic time-series prediction on the Lorenz system.<n>We formalize a temporal windowing technique within the QRC pipeline that improves attractor reconstruction.<n>Our findings suggest the fixed-reservoir architecture is a primary driver of QRC's advantage at these scales.
  arXiv  Detail & Related papers  (2026-04-26T14:43:03Z)
• Blind Catalytic Quantum Error Correction: Target-State Estimation and Fidelity Recovery Without \textit{A Priori} Knowledge [0.0]
  We introduce emphblind CQEC, which estimates the target from the noisy output alone before catalytic recovery.<n>Five estimation strategies are benchmarked across three noise models.
  arXiv  Detail & Related papers  (2026-04-13T08:27:08Z)
• Layer-wise QUBO-Based Training of CNN Classifiers for Quantum Annealing [0.0]
  We propose an iterative framework based on Quadratic Un Binary Optimization (QUBO) for training the head of convolutional neural networks (CNNs)<n>A per-output decomposition splits the $C$-class problem into $C$ independent QUBOs, each with $(d+1)K$ binary variables, where $d$ is the feature dimension and $K$ is the bit precision.<n>We evaluate the method on six image-classification benchmarks (sklearn digits, MNIST, Fashion-MNIST, CIFAR-10, EMNIST, KMNIST)
  arXiv  Detail & Related papers  (2026-03-03T13:10:36Z)
• Benchmarking Quantum and Classical Algorithms for the 1D Burgers Equation: QTN, HSE, and PINN [0.0]
  We present a comparative benchmark of Quantum Networks (QTN), the Hydrodynamic Schrdinger Equation (Difference), and Physics-Informed Neural Networks (PINN) for simulating the 1D Burgers' equation.<n>We analyse solution accuracy, runtime scaling, and resource overhead across grid resolutions ranging from $N=4$ to $N=128$.
  arXiv  Detail & Related papers  (2026-02-04T05:57:27Z)
• A Comparative Study of Encoding Strategies for Quantum Convolutional Neural Networks [0.0]
  Quantum convolutional neural networks (QCNNs) offer a promising architecture for near-term quantum machine learning.<n>However, any QCNN operating on classical data must rely on an encoding scheme to embed inputs into quantum states.<n>This work presents an implementation-level comparison of three representative encodings -- Angle, Amplitude, and a Hybrid phase/angle scheme.
  arXiv  Detail & Related papers  (2025-12-14T01:31:16Z)
• Towards large-scale quantum optimization solvers with few qubits [59.63282173947468]
  We introduce a variational quantum solver for optimizations over $m=mathcalO(nk)$ binary variables using only $n$ qubits, with tunable $k>1$. We analytically prove that the specific qubit-efficient encoding brings in a super-polynomial mitigation of barren plateaus as a built-in feature.
  arXiv  Detail & Related papers  (2024-01-17T18:59:38Z)
• Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian [72.57870177599492]
  We propose a SE(3)-equivariant network, named QHNet, that achieves efficiency and equivariance. Our key advance lies at the innovative design of QHNet architecture, which not only obeys the underlying symmetries, but also enables the reduction of number of tensor products by 92%. Experimental results show that our QHNet can achieve comparable performance to the state of the art methods at a significantly faster speed.
  arXiv  Detail & Related papers  (2023-06-08T03:47:33Z)
• Scalable Lipschitz Residual Networks with Convex Potential Flows [120.27516256281359]
  We show that using convex potentials in a residual network gradient flow provides a built-in $1$-Lipschitz transformation. A comprehensive set of experiments on CIFAR-10 demonstrates the scalability of our architecture and the benefit of our approach for $ell$ provable defenses.
  arXiv  Detail & Related papers  (2021-10-25T07:12:53Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.