Reproduce “Neural Fourier Surrogates for Data Reuploading Quantum Neural Networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Oliver Knitter, Jonathan Mei, Sang Hyub Kim, Chi Chen, Masako Yamada, Martin Roetteler
The authors introduce Neural Fourier Surrogates (NFS) as a classical baseline for data-reuploading quantum neural networks (QNNs). NFS learns a distribution over the finite Fourier frequencies used by a QNN, rather than enumerating every coefficient. On six tabular learning curves, NFS and QNNs perform broadly similarly. This does not show general quantum-classical equivalence; NFS can learn broader coefficients.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.