Quantum Generative Diffusion Model for Real-World Time Series

2026-06-25

AI Summary

This work addresses the high computational cost, large parameter count, and low efficiency of classical generative diffusion models in time series synthesis by proposing QDiffusion-TS—the first quantum generative diffusion model tailored for real-world time series. The approach introduces a hybrid quantum Transformer architecture by replacing the feedforward modules in a denoising Transformer with quantum neural networks, thereby pioneering the integration of quantum neural networks into time series diffusion generation. Experiments on an IQM quantum processor demonstrate that the model reduces the number of trainable parameters by nearly three orders of magnitude while significantly improving generation quality—evidenced by a 44% reduction in Wasserstein distance—and enhancing downstream forecasting performance, achieving a 71% improvement in RMSE over baseline methods on Apple and Amazon financial datasets.

Abstract

Generative models have achieved remarkable success in data synthesis, though recent advances driven by increasing model scale have introduced challenges in computational cost and efficiency. Quantum machine learning offers a promising alternative, representing complex data distributions using compact, highly expressive models. Here, we propose QDiffusion-TS, the first quantum generative diffusion model for time series synthesis, and validate it on the IQM quantum processor. The framework extends a classical diffusion architecture by replacing feed-forward components within the denoising transformer with quantum neural networks, yielding a hybrid quantum transformer that reduces the number of trainable parameters in each replaced component by nearly three orders of magnitude. Evaluated on financial time series from Apple and Amazon, the model generates synthetic data that more accurately reproduces the real distributions, reducing Wasserstein distance by approximately 44% relative to its classical counterpart across both datasets. In a downstream forecasting task, augmentation with the generated data improves predictive performance by up to 71% in RMSE over a baseline trained solely on real data. These results show that quantum enhanced architectures can consistently match and frequently surpass classical performance with substantially fewer parameters, establishing a practical framework towards more efficient and scalable data-driven generative modelling.

Problem

• quantum generative model
• time series synthesis
• diffusion model
• data efficiency
• computational cost

Innovation

• quantum generative diffusion
• time series synthesis
• quantum neural networks
• hybrid quantum-classical model
• parameter-efficient generative modeling