Spectral Quantum Memory for Implicit Neural Representations
quant-ph, cs.AI, cs.LG
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: Accepted to Neurips 2026
Code: https://github.com/Kiiwii10/SQMM
License: http://creativecommons.org/licenses/by/4.0/
The gist: Implicit neural representations (INRs) model signals as continuous functions from coordinates to values, but their performance depends strongly on how spectral capacity is allocated.
Abstract
Implicit neural representations (INRs) model signals as continuous functions from coordinates to values, but their performance depends strongly on how spectral capacity is allocated. Yet most Quantum INR (QINR) architectures treat spectral components as independent outputs of separate quantum blocks. We introduce the Spectral Quantum Memory Model (SQMM), a memory coupled quantum INR in which sequential hybrid data reuploading layers (bands) communicate through a shared coherent quantum memory register. Each band reads the memory, computes on its own coordinate upload, and writes part of its state back, so later bands can build on the computation of earlier ones. When memory read and write layers are input independent, we prove that the memory state forms an operator valued Fourier series whose support is contained in the Minkowski sum of the initial memory spectrum and the local band spectra. Downstream bands then condition their Fourier coefficients on the spectral content stored by earlier bands, and the memory coupling creates no new primitive frequencies. This theory motivates a spectral memory alignment loss that encourages memory to encode the spectrum expressed by the deployed prefix of the model. Across audio and image reconstruction benchmarks, SQMM improves over compact QINR and INR baselines.
Sources
- PennyLane: Automatic differentiation of hybrid quantum-classical computations
- COIN: COmpression with Implicit Neural representations
- Classification with Quantum Neural Networks on Near Term Processors
- Quantum Self-Attention Neural Networks for Text Classification
- Implicit Neural Representations with Fourier Kolmogorov-Arnold Networks
- Data re-uploading with a single qudit
- Fourier Analysis of Variational Quantum Circuits for Supervised Learning
- Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
- Reconstructing continuous distributions of 3D protein structure from cryo-EM images
Related papers
- Computational regimes in matrix-product-state-based quantum trajectory simulations
- Toward chemically accurate quantum simulations on quantum hardware: A quantum-HPC hybrid approach
- Transversal surface-code game with reconfigurable qubits
- Fulqrum: a generalized framework for quantum subspace diagonalization
- Flux-Activated Resonant Control of a Bosonic Quantum Memory
- Machine learning the effects of many quantum measurements