Quantum-Noise-Driven Generative Diffusion Models

Year: 2024

Authors: Parigi M., Martina S., Caruso F.

Autors Affiliation: Univ Florence, Dept Phys & Astron, Via Sansone 1, I-50019 Florence, Italy; Univ Florence, LENS European Lab Nonlinear Spect, Via Nello Carrara 1, I-50019 Florence, Italy; Ist Nazl Ott Consiglio Nazl Ric CNR INO, I-50019 Sesto Fiorentino, Italy.

Abstract: 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

Journal/Review: ADVANCED QUANTUM TECHNOLOGIES

More Information: M.P. and S.M. acknowledged financial support from PNRR MUR project PE0000023-NQSTI. F.C. also acknowledged financial support by the European Commission’s HORIZON EUROPE Framework Programme under the Research and Innovation Action GA n. 101070546-MUQUABIS, by the European Union’s Horizon 2020 research and innovation programme under FET-OPEN GA n. 828946-PATHOS, by the European Defence Agency under the project Q-LAMPS Contract No B PRJ-RT-989, and under the National Recovery and Resilience Plan (NRRP), Mission 4, Component 2, Investment 1.1, Call for tender No. 104 published on 2.2.2022 by the Italian Ministry of University and Research (MUR), funded by the European Union NextGenerationEU Project Title Trustworthy hybrid quantum-classical Artificial Intelligence for Medical Image Analysis (ThAI-MIA) CUP B53D23005000006.
KeyWords: diffusion models; generative models; quantum computing; quantum machine learning; quantum noise
DOI: 10.1002/qute.202300401

Citations: 3
data from “WEB OF SCIENCE” (of Thomson Reuters) are update at: 2024-11-24
References taken from IsiWeb of Knowledge: (subscribers only)

Connecting to view paper tab on IsiWeb: Click here
Connecting to view citations from IsiWeb: Click here