IFML Diffusion Seminar Series: Tutorial on the Mathematical Foundations of Diffusion Models for Image Generation

In the first talk of the new IFML Diffusion Seminar Series, Sanjay Shakkottai presents "Tutorial on the Mathematical Foundations of Diffusion Models for Image Generation."

Watch the presentation here.
Download a PDF of the presentation here.

Abstract: Diffusion models have emerged as a powerful new approach to generative modeling of images. We will discuss the basic mathematical models and techniques that underlie diffusions. Topics covered will include an overview of stochastic differential equations, a derivation of the Fokker-Planck equation, forward and reverse processes, learning score functions through Tweedie’s formula, and deriving ODE flow models (using the Fokker-Planck equation).

Speaker Bio: Sanjay Shakkottai received his Ph.D. from the ECE Department at the University of Illinois at Urbana-Champaign in 2002. He is with The University of Texas at Austin, where he is a Professor in the Chandra Family Department of Electrical and Computer Engineering, and holds the Cockrell Family Chair in Engineering #15. He is also the Director of the Center for Generative AI, a campus-wide computing cluster at UT Austin. He received the NSF CAREER award in 2004 and was elected as an IEEE Fellow in 2014. He was a co-recipient of the IEEE Communications Society William R. Bennett Prize in 2021. He has served as the Editor in Chief of IEEE/ACM Transactions on Networking. His research interests lie at the intersection of  statistical learning and algorithms for resource allocation, with applications to generative models and wireless communication networks.