Leveraging Quantum Measurement Randomness for Shot-Efficient Diffusion Models
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 shots per sample against a high-shot reference of , about fewer. Latent diffusion experiments on MNIST further validate the proposed mechanism for generation in a learned latent space.
Figures & tables
| readout | params | shots | ||
|---|---|---|---|---|
| Logarithmic encoding, | ||||
| Fixed affine | ||||
| diagonal | ||||
| Per-dimension encoding, | ||||
| fixed | ||||
| encoding | time | ||
|---|---|---|---|
| amplitude | on | ||
| probability | on | ||
| hybrid | on | ||
| amplitude | off | ||
| probability | off | ||
| hybrid | off |
| Gaussian mixture | MNIST latent | |||
|---|---|---|---|---|
| log. | per-dim | log. | per-dim | |
| qubits | ||||
| re-uploading layers | ||||
| single-qubit gates | ||||
| two-qubit gates | ||||
| reverse steps | ||||
Quantum Generative Modeling
Quantum generative modeling uses quantum circuits and quantum-inspired methods to learn and sample data distributions and quantum states.
See all 60 papers