arXiv：cs.LG（机器学习，全量分类）· Oliver Knitter, Jonathan Mei, Sang Hyub Kim, Chi Chen, Masako Yamada, Martin Roetteler·· 11 小时前AI 评分34
Neural Fourier Surrogates：为数据重上传量子神经网络提供经典基线
Neural Fourier Surrogates for Data Reuploading Quantum Neural Networks
AI 导读
研究提出 Neural Fourier Surrogates（NFS），一种随机经典神经网络架构，可在与量子神经网络相同的有限傅里叶级数支撑上高效学习系数。在多个表格基准数据集上，NFS 分类性能与 Random Fourier Features 模型等经典基线相当，并与数据重上传 QNN 表现接近。结合合成数据上傅里叶谱的对比分析，NFS 可作为评估 QNN 性能的天然经典基线。
正文
Abstract:For quantum machine learning, the exact boundary between classical and quantum advantage is still poorly understood. Direct comparison between quantum neural networks (QNNs) and existing classical models, which encompass fundamentally different function classes, often fails to provide broader insight into the difference between the two. Inspired by the techniques of Neural Quantum States and Random Fourier Features, this work introduces Neural Fourier Surrogates (NFS), a stochastic classical neural network architecture for efficiently learning coefficients over the same finite Fourier series support as quantum neural networks. Testing on a selection of tabular benchmark datasets, we find that NFS is an effective classifier architecture broadly competitive with established classical baselines, including a comparable Random Fourier Features model, and possessing comparable performance to data-reuploading QNNs; combined with additional analysis comparing the learned Fourier spectra of QNNs and NFS on synthetic data, these results establish NFS as a natural classical baseline for evaluating QNN performance.
| Comments: | 10 pages, 5 figures, 2 tables |
| Subjects: | Quantum Physics (quant-ph); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00841 [quant-ph] |
| (or arXiv:2610.00841v1 [quant-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00841 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Oliver Knitter [view email]
[v1]
Wed, 30 Sep 2026 23:56:20 UTC (121 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org