Quantum-Noise-Driven Generative Diffusion Models

Abstract

Generative models realized with machine learning 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 are an emerging framework that have recently overcome the performance of the generative adversarial networks in creating synthetic text and high-quality images. Here, we propose and discuss the quantum generalization of diffusion models, i.e., three quantum-noise-driven generative diffusion models 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, we suggest to exploit quantum noise not as an issue to be detected and solved but instead as a very remarkably beneficial key ingredient to generate much more complex probability distributions that would be difficult or even impossible to express classically, and from which a quantum processor might sample more efficiently than a classical one. An example of numerical simulations for an hybrid classical-quantum generative diffusion model is also included. Therefore, our results are expected to pave the way for new quantum-inspired or quantum-based generative diffusion algorithms addressing more powerfully classical tasks as data generation/prediction with widespread real-world applications ranging from climate forecasting to neuroscience, from traffic flow analysis to financial forecasting.

27 pages, 4 figures

References in corpus (12)

• Charge insensitive qubit design derived from the Cooper pair box
• Diffusion Models in Vision: A Survey
• Suppressing Charge Noise Decoherence in Superconducting Charge Qubits
• Quantum Data Fitting
• Quantum computing with neutral atoms
• Noise-enhanced classical and quantum capacities in communication networks
• Generative quantum machine learning via denoising diffusion probabilistic models
• A Framework for Demonstrating Practical Quantum Advantage: Racing Quantum against Classical Generative Models
• Quantum Reinforcement Learning: the Maze problem
• Experimental quantum pattern recognition in IBMQ and diamond NVs
• Deep learning enhanced noise spectroscopy of a spin qubit environment
• Machine-learning based noise characterization and correction on neutral atoms NISQ devices

Cited by in corpus (8)

• Distributed quantum architecture search
• Quantum Latent Diffusion Models
• Towards Efficient Quantum Hybrid Diffusion Models
• The role of data embedding in equivariant quantum convolutional neural networks
• Permutation-equivariant quantum convolutional neural networks
• Machine-learning based high-bandwidth magnetic sensing
• Stochastic Schrödinger Equations for Quantum Reverse Diffusion
• Identification of quantum generative circuits with parallel quantum neural network