Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support

• URL: http://arxiv.org/abs/2607.22516v1
• Date: Fri, 24 Jul 2026 17:39:14 GMT
• Title: Quantum Spectral Model: Data Reuploading with Input-Conditioned Frequency Support
• Abstract summary: We introduce Quantum Spectral Models (QSMs), in which we construct the generator of the data-encoding unitary directly from each input matrix.<n>We study three QSM variants based on symmetric, global block, and non-overlapping patch-local block Hamiltonians.<n>Our results shed new light on quantum machine-learning model design by showing how input-conditioned spectral representations can provide an analysable inductive bias.
• Score: 1.338174941551702
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: A central design principle in modern machine learning and artificial intelligence is to align a model's inductive bias with the structure of its input data. For matrix-valued inputs, relevant matrix-level relationships can be characterised through spectral values and spectral subspaces; however, common coordinate-wise rotation-gate data-encoding unitaries used in most quantum machine learning models do not explicitly construct such a matrix-level representation. We introduce Quantum Spectral Models (QSMs), in which we construct the generator of the data-encoding unitary directly from each input matrix. We study three QSM variants based on symmetric, global block, and non-overlapping patch-local block Hamiltonians. Their outputs admit truncated Fourier representations in which input-dependent spectral gaps supply candidate phase carriers, while spectral subspaces help determine their coefficients. We evaluate the QSMs and comparison quantum models on two matrix representations of Pendigits and two controlled synthetic tasks defined by spectral statistics. At the largest evaluated circuit depth, QSM variants lead the tested quantum models in mean test accuracy across all four benchmarks. The patch-local QSM leads on Pendigits, whereas the global block-Hamiltonian QSM leads on the controlled spectral tasks. Ablations show a task-dependent reversal: subspace-preserving controls perform better on Pendigits, whereas spectral-value-only controls lead among the tested ablations on the synthetic tasks. Together, these results shed new light on quantum machine-learning model design by showing how input-conditioned spectral representations can provide an analysable inductive bias, while offering a broader perspective on structure-aware model design in machine learning and artificial intelligence.

Related papers

• Learning Metamaterial Eigenmodes with Wavelet-Encoded Fourier Neural Operators [57.64362886310329]
  We show that a machine learning surrogate based on neural operators can learn and predict multiple eigenmodes of the elastic wave equation.<n>For metamaterial design, the resulting surrogate accelerates the simulation stage of the design cycle by three orders of magnitude relative to finite element analysis on a consumer-grade CPU.<n>These results also carry broader implications for designing input encodings in other multi-mode PDE solvers based on spectral neural operators.
  arXiv  Detail & Related papers  (2026-09-08T01:21:46Z)
• Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers [56.376795859825705]
  Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data.<n>Previous DFQ arts for Vision Transformers (ViTs) often suffer from a distribution mismatch between synthetic samples and input distribution expected by quantized models Q.<n>We propose a novel Masked Attention Alignment approach for Data-Free Quantization of ViTs, named MaskAQ.
  arXiv  Detail & Related papers  (2026-06-03T02:38:19Z)
• Trainable Quantum Spectral Models for Partial Differential Equations [0.0]
  We study trainable quantum spectral models (QSMs) for solving linear partial differential equations (PDEs)<n>Instead of learning solutions directly in physical space, QSMs learn the inverse differential operator in a spectral representation, embedding prior knowledge of the equation's natural basis.<n>Our results identify operator-aware spectral representations as a promising route toward trainable and physically grounded quantum methods for scientific computing.
  arXiv  Detail & Related papers  (2026-05-29T12:47:50Z)
• Beyond Gates: Pulse Level Quantum Fourier Models [1.0482211230201115]
  We evaluate quantum Fourier models (QFMs) through the lens of pulse parameters.<n>We show that control over pulse shapes does not significantly alter the global expressibility or structural correlations of the Ansatz.<n>For composite gates, independent pulse scalings replace a single logical angle by multiple independently tunable sub-angles.
  arXiv  Detail & Related papers  (2026-05-06T14:13:44Z)
• Quantum Visual Fields with Neural Amplitude Encoding [70.86293548779774]
  We introduce a new type of Quantum Implicit Neural Representation (QINR) for 2D image and 3D geometric field learning.<n>QVF encodes classical data into quantum statevectors using neural amplitude encoding grounded in a learnable energy manifold.<n>Our ansatz follows a fully entangled design of learnable parametrised quantum circuits, with quantum (unitary) operations performed in the real Hilbert space.
  arXiv  Detail & Related papers  (2025-08-14T17:59:52Z)
• Are queries and keys always relevant? A case study on Transformer wave functions [0.0]
  dot product attention mechanism, originally designed for natural language processing tasks, is a cornerstone of modern Transformers.<n>We explore the suitability of Transformers, focusing on their attention mechanisms, in the specific domain of the parametrization of variational wave functions.
  arXiv  Detail & Related papers  (2024-05-29T08:32:37Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• QuDPy: A Python-Based Tool For Computing Ultrafast Non-linear Optical Responses [5.787049285733455]
  We present the initial release of our code, QuDPy (quantum dynamics in python) An important feature of our approach is that one can specify various high-order optical response pathways. We use the quantum dynamics capabilities of QuTip for simulating the spectral response of complex systems.
  arXiv  Detail & Related papers  (2022-10-28T18:44:52Z)
• Unsupervised Interpretable Learning of Phases From Many-Qubit Systems [2.4352963290061993]
  We show how an unsupervised machine-learning technique can be used to understand short-range entangled many-qubit systems. Our work opens the door for a first-principles application of hybrid algorithms that aim at strong interpretability without supervision.
  arXiv  Detail & Related papers  (2022-08-18T14:35:28Z)
• QSAN: A Near-term Achievable Quantum Self-Attention Network [73.15524926159702]
  Self-Attention Mechanism (SAM) is good at capturing the internal connections of features. A novel Quantum Self-Attention Network (QSAN) is proposed for image classification tasks on near-term quantum devices.
  arXiv  Detail & Related papers  (2022-07-14T12:22:51Z)
• Simulating nonnative cubic interactions on noisy quantum machines [65.38483184536494]
  We show that quantum processors can be programmed to efficiently simulate dynamics that are not native to the hardware. On noisy devices without error correction, we show that simulation results are significantly improved when the quantum program is compiled using modular gates.
  arXiv  Detail & Related papers  (2020-04-15T05:16:24Z)

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.