Quantum Circuits in Diffusion Models: A Fair-Comparison Study and a Mechanistic Analysis of Angle-Embedding Failures

• URL: http://arxiv.org/abs/2607.09108v1
• Date: Fri, 10 Jul 2026 05:45:20 GMT
• Title: Quantum Circuits in Diffusion Models: A Fair-Comparison Study and a Mechanistic Analysis of Angle-Embedding Failures
• Abstract summary: We study the integration of variational quantum circuits (VQCs) into diffusion models through a squeeze-and-excitation (SE) channel-modulation scaffold.<n>We find that quantum cores achieve comparable mean FID to the classical control across DDPM and latent diffusion, while paired sampling-seed tests for EfficientSU2 detect no statistically significant difference.
• Score: 0.42970700836450487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the integration of variational quantum circuits (VQCs) into diffusion models through a squeeze-and-excitation (SE) channel-modulation scaffold that isolates the quantum contribution. Using a role-matched classical control and multi-seed significance testing across DDPM and latent diffusion on MNIST and CIFAR-10, with a score-based NCSN study on MNIST, we find that quantum cores achieve comparable mean FID to the classical control across DDPM and latent diffusion, while paired sampling-seed tests for EfficientSU2 detect no statistically significant difference. Although the quantum cores use $4.5$--$9\times$ fewer core parameters than the role-matched control, parameter-matched classical controls attain comparable mean FID, so the experiments do not establish a quantum parameter-efficiency advantage. We further identify a structural failure in score-based NCSN: the unbounded score target, proportional to $1/σ$, drives angle-embedding inputs far beyond the $2π$ period of rotation gates, causing phase aliasing and collapse of the quantum modulator. A bounding transformation, $θ\leftarrow π\tanh(\cdot)$, maps inputs to the non-aliasing domain and substantially improves both quantum cores. Since all circuits are classically simulated at a few-qubit scale, we do not claim quantum advantage. Instead, the study provides a fair-comparison protocol for quantum-enhanced generative models and a mechanistic account of when and why angle embeddings fail.

Related papers

• How Quantum Is the Advantage? A Fair, Calibration- and Noise-Aware Benchmark and Attribution Audit of Quantum Machine Learning for Network Intrusion Detection [0.0]
  Quantum machine learning for network intrusion detection is routinely reported to reach near-perfect accuracy.<n>Most rigorous studies find that well-tuned classical models remain competitive.<n>We present a unified, reproducible QML-IDS benchmark evaluating hybrid variational quantum circuits.
  arXiv  Detail & Related papers  (2026-08-13T07:44:35Z)
• Quantum-classical crossover in fault-tolerant quantum dynamics simulation [56.198154828333685]
  We introduce a scalable fault-tolerant framework that combines coherent observable estimation with a space-time-efficient implementation of non-Clifford rotations.<n>A benchmark against state-of-the-art tensor-network and variational Monte Carlo algorithms reveals a concrete crossover for mixed-field Ising dynamics.
  arXiv  Detail & Related papers  (2026-07-17T16:54:25Z)
• Designing quantum technologies with a quantum computer [1.4951795042951048]
  We develop a quantum-computer-aided framework for simulating devices using a general electron spin resonance Hamiltonian.<n>Within this model, we combine Gray-encoded qudit-to-qubit mappings, qubit-wise commuting aggregation, and a multi-reference selected quantum Krylov fast-forwarding algorithm.<n> Numerical simulations demonstrate the computation of autocorrelation functions up to $sim100$ ns, together with microwave absorption spectra.<n>We benchmark the framework against classical simulations and identify the reference-state selection in sQKFF as the primary factor governing accuracy at fixed hardware cost.
  arXiv  Detail & Related papers  (2026-01-29T18:26:54Z)
• Mitigating Barren plateaus in quantum denoising diffusion probabilistic models [49.90716699848553]
  Quantum generative models leverage quantum superposition and entanglement to enhance learning efficiency for both classical and quantum data.<n>QuDDPM has been proposed as a promising framework for quantum generative learning.<n>We show that barren plateaus emerge in QuDDPMs due to the use of 2-design states as the input for the denoising process.<n>We introduce an improved QuDDPM that utilizes a distribution maintaining a certain distance from the Haar distribution, ensuring better trainability.
  arXiv  Detail & Related papers  (2025-12-07T07:01:44Z)
• Towards Quantum Enhanced Adversarial Robustness with Rydberg Reservoir Learning [45.92935470813908]
  Quantum computing reservoir (QRC) leverages the high-dimensional, nonlinear dynamics inherent in quantum many-body systems.<n>Recent studies indicate that perturbation quantums based on variational circuits remain susceptible to adversarials.<n>We investigate the first systematic evaluation of adversarial robustness in a QR based learning model.
  arXiv  Detail & Related papers  (2025-10-15T12:17:23Z)
• Quantum algorithms to detect ODMR-active defects for quantum sensing applications [4.574603767529566]
  We propose two quantum algorithms to detect an imbalance in the triplet-to-singlet intersystem crossing rates.<n>We show that the ISC rate imbalance can be detected with as few as 105 logical qubits and $2.2 times 108$ Toffoli gates.
  arXiv  Detail & Related papers  (2025-08-18T18:00:37Z)
• Calibration of Quantum Devices via Robust Statistical Methods [45.464983015777314]
  We numerically analyze advanced statistical methods for Bayesian inference against the state-of-the-art in quantum parameter learning.<n>We show advantages of these approaches over existing ones, namely under multi-modality and high dimensionality.<n>Our findings have applications in challenging quantumcharacterization tasks namely learning the dynamics of open quantum systems.
  arXiv  Detail & Related papers  (2025-07-09T15:22:17Z)
• Quantum Generative Diffusion Model: A Fully Quantum-Mechanical Model for Generating Quantum State Ensemble [40.06696963935616]
  We introduce Quantum Generative Diffusion Model (QGDM) as their simple and elegant quantum counterpart. QGDM exhibits faster convergence than Quantum Generative Adversarial Network (QGAN) It can achieve 53.02% higher fidelity in mixed-state generation than QGAN.
  arXiv  Detail & Related papers  (2024-01-13T10:56:34Z)
• Shallow unitary decompositions of quantum Fredkin and Toffoli gates for connectivity-aware equivalent circuit averaging [0.0]
  Controlled-SWAP and controlled-controlled-NOT gates are at the heart of the original proposal of reversible classical computation. We provide several logically equivalent circuits for the Toffoli and Fredkin gates under all-to-all and linear qubit connectivity. We also demonstrate the remarkable effectiveness of the obtained decompositions at mitigating coherent errors on near-term quantum computers.
  arXiv  Detail & Related papers  (2023-05-29T14:46:19Z)
• QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks [124.7972093110732]
  We propose quantum graph convolutional networks (QuanGCN), which learns the local message passing among nodes with the sequence of crossing-gate quantum operations. To mitigate the inherent noises from modern quantum devices, we apply sparse constraint to sparsify the nodes' connections. Our QuanGCN is functionally comparable or even superior than the classical algorithms on several benchmark graph datasets.
  arXiv  Detail & Related papers  (2022-11-09T21:43:16Z)
• A comparison between quantum and classical noise radar sources [0.07829352305480283]
  We compare the performance of a quantum radar based on two-mode squeezed states with a classical radar system based on correlated thermal noise. With a constraint of equal number of photons $N_S$ transmitted to probe the environment, we find that the quantum setup exhibits an advantage with respect to its classical counterpart.
  arXiv  Detail & Related papers  (2020-08-28T15:45:34Z)
• Probing the Universality of Topological Defect Formation in a Quantum Annealer: Kibble-Zurek Mechanism and Beyond [46.39654665163597]
  We report on experimental tests of topological defect formation via the one-dimensional transverse-field Ising model. We find that the quantum simulator results can indeed be explained by the KZM for open-system quantum dynamics with phase-flip errors. This implies that the theoretical predictions of the generalized KZM theory, which assumes isolation from the environment, applies beyond its original scope to an open system.
  arXiv  Detail & Related papers  (2020-01-31T02:55:35Z)

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.