Quantum-Noise-Driven Generative Diffusion Models

arXiv:2308.12013v3 Announce Type: replace-cross
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 …

abstract adversarial arxiv cond-mat.dis-nn cs.ai cs.lg data diffusion diffusion models framework generative generative adversarial networks generative models machine machine learning machine learning techniques networks noise performance quant-ph quantum replace samples stat.ml synthetic synthetic data tools training type