quant-phOct 30, 2026

Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models

Authors: Tianhao Guo, Dianxin Zheng, Yuhua Qian, Yaohui Zheng, Yuzhi Yang, Merouane Debbah, Chau Yuen

Organizations: College of Physics and Electronic Engineering and the Shanxi Key Laboratory of Wireless Communication and Detection, Shanxi University, Taiyuan 030006, China · National Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, China · Institute of Big Data Science and Industry, Key Laboratory of Evolutionary Science Intelligence of Shanxi Province, School of Artificial Intelligence, Shanxi University, Taiyuan 030006, China · State Key Laboratory of Quantum Optics Technologies and Devices, Institute of Opto-Electronics, Shanxi University, Taiyuan 030006, China · 

Abstract

In quantum computing, the readout always carries finite-shot sampling noise. Suppressing this noise through repeated measurements raises the cost of a quantum neural network (QNN). Meanwhile, a stochastic diffusion sampler deliberately adds randomness at each reverse (generation) step. This paper turns the measurement noise from a liability into a resource. Specifically, we use the noise quantum measurement produces anyway to replace part of the noise the sampler would otherwise inject. We characterize the measurement error as multinomial sampling noise propagated through a trainable linear readout. To connect the circuit's Born probabilities to the denoising task, we further formulate the diffusion process on a bounded zero-sum hyperplane mapped to the probability simplex. Therefore, we can employ a compensation noise to match the mean and covariance of the shot-noise-free linear update under some minimum shot conditions. Solving this condition for the shot count gives a state-dependent adaptive budget. For the denoising diffusion implicit model (DDIM), this budget increases as the sampler becomes more deterministic. On an eight-dimensional Gaussian mixture, the schedule achieves comparable generation quality with 303303 shots per sample against a high-shot reference of 1.6×1061.6\times10^{6}, about 5300×5300\times fewer. Latent diffusion experiments on MNIST further validate the proposed mechanism for generation in a learned latent space.

Figures & tables

Explore similar work

CardsList
  1. Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion

    May 28, 2025Marco Parigi, Stefano Martina, Francesco Aldo Venturelli +1Quantum Generative ModelingDiffusion-Based Image Generation

  2. An Hybrid Quantum-Classical Diffusion Model for Image Generation

    Jul 8, 2026Qipeng Qian, Keli Deng, Yuntao QianLatent Diffusion ModelsQuantum Generative Modeling

  3. Learning Quantum Data Distribution via Chaotic Quantum Diffusion Model

    Feb 25, 2026Quoc Hoan Tran, Koki Chinzei, Yasuhiro Endo +1Quantum Generative ModelingDiffusion Models