Theoretical research on generative diffusion models: an overview
It addresses the need for a theoretical synthesis in generative diffusion models for researchers, but it is incremental as it builds on existing reviews by focusing on algorithmic aspects.
The paper provides an overview of theoretical developments in generative diffusion models, categorizing them into training-based and sampling-based approaches to offer a clear framework for future research.
Generative diffusion models showed high success in many fields with a powerful theoretical background. They convert the data distribution to noise and remove the noise back to obtain a similar distribution. Many existing reviews focused on the specific application areas without concentrating on the research about the algorithm. Unlike them we investigated the theoretical developments of the generative diffusion models. These approaches mainly divide into two: training-based and sampling-based. Awakening to this allowed us a clear and understandable categorization for the researchers who will make new developments in the future.