Persons and affiliations

Date

Description

Innovations in machine learning have brought advancements in other engineering fields employing machine learning as well, and the area of communications is one of them. Diffusion models have drawn enormous attention as a potent generative model and demonstrated remarkable sample quality, particularly in computer vision. In the communication engineering field, recent studies employed generative models to solve complicated problems such as to synthesize the channel distribution, to learn optimal designs of channel codes and signaling schemes, to remove channel noise and distortion, to optimize beamforming, etc. The emergence of diffusion models opened up the possibility of further development of such topics. This tutorial aims at providing an introduction of diffusion denoising probabilistic models and reviewing the application of diffusion models in communication engineering.