Quantum-Noise-Driven Generative Diffusion Models

Generative models realized with Machine Learning (ML) techniques are powerful tools to infer complex and unknown data distributions from a finite number of training samples in order to produce new synthetic data. Diffusion Models (DMs) are an emerging framework that have recently overcome Generative Adversarial Networks (GANs) in creating high-quality images. Here, is proposed and discussed the quantum generalization of DMs, i.e., three Quantum-Noise-Driven Generative Diffusion Models (QNDGDMs) that could be experimentally tested on real quantum systems. The idea is to harness unique quantum features, in particular the non-trivial interplay among coherence, entanglement, and noise that the currently available noisy quantum processors do unavoidably suffer from, in order to overcome the main computational burdens of classical diffusion models during inference. Hence, the suggestion is to exploit quantum noise not as an issue to be detected and solved but instead as a beneficial key ingredient to generate complex probability distributions from which a quantum processor might sample more efficiently than a classical one. Three examples of the numerical simulations are also included for the proposed approaches. The results are expected to pave the way for new quantum-inspired or quantum-based generative diffusion algorithms addressing tasks as data generation with widespread real-world applications.Diffusion Models (DMs) are today a very popular class of generative models for Machine Learning (ML), using a noisy dynamics to learn an unknown density probability of a finite set of samples in order to generate new synthetic data. This study proposes a method to generalize them into the quantum domain by introducing and investigating what are termed Quantum-Noise-Driven Generative Diffusion Models (QNDGDMs). image