← Back to all news
arXiv Machine Learning By Tianhao Guo, Dianxin Zheng, Yuhua Qian, Yaohui Zheng, Yuzhi Yang, Merouane Debbah, Chau Yuen

Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models

Read the original on arXiv Machine Learning →

The paper proposes using the inherent shot‑noise from quantum measurements as a resource for diffusion models, replacing part of the stochastic noise normally injected during generation. By modeling measurement error as multinomial sampling noise and mapping the diffusion process onto a bounded hyperplane, the authors derive a state‑dependent adaptive shot budget that matches the mean and covariance of a shot‑noise‑free update. Experiments on an eight‑dimensional Gaussian mixture and MNIST latent diffusion demonstrate that this approach achieves comparable generation quality with dramatically fewer shots—down to 303 shots per sample versus 1.6 × 10⁶ in a high‑shot baseline.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
1d ago

Noise-regularized training of quantum circuit Born machines under a finite shot budget

The paper investigates how hardware noise influences the generalization ability of quantum circuit Born machines (QCBMs) trained with maximum mean discrepancy. It establishes that the generalization gap is bounded by the complexity of distributions reachable under any noise process, and shows that scrambled local Pauli noise reduces this complexity while biasing the model toward uniformity, thereby acting as a regularizer with an optimal intermediate strength. The authors introduce GENIE, a framework that implements a target noise level with capped error mitigation and dynamically selects the optimal noise during training using held‑out data, achieving provably bounded regret and outperforming fixed‑noise strategies in simulations on synthetic and census datasets.

By Hoang M. Ngo, Quan Nguyen, Jung Taek Seo, Wanli Xing, My T. Thai
More like this →
arXiv Machine Learning
Sep 3

Quantum MeanFlow: single-shot generative sampling on NISQ hardware

Quantum MeanFlow (QMF) is a new quantum generative sampling method that enables single‑step sample generation by learning an average velocity field over a time interval, unlike the multi‑step quantum flow matching (QFM) which requires sequential integration of an ordinary differential equation. Using parameterized quantum circuits, the authors benchmark QMF and QFM on the MNIST dataset, finding that QMF produces lower image quality than multi‑step QFM but outperforms single‑step QFM at every shot count. Both models were executed on IBM quantum computers, and best‑of‑N rejection sampling mitigates device noise without circuit modification, demonstrating QMF’s practicality for efficient single‑step quantum generative sampling.

By Ashish Joshi, Eshaan Mistry, Takahiko Koyama
diffusionbenchmarks
More like this →
arXiv AI
Oct 12

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

The paper presents two physics-inspired protocols for quantum diffusion models (QDMs) in generative AI. The first protocol employs quantum stochastic walks, combining quantum and classical dynamics to produce MNIST image sets with lower Fréchet Inception Distance than purely classical dynamics. The second protocol uses the intrinsic noise of real IBM quantum hardware with only four qubits to generate images, suggesting that quantum noise can be exploited as a resource rather than mitigated.

By Marco Parigi, Stefano Martina, Francesco Aldo Venturelli, Filippo Caruso
diffusion
More like this →