BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Diffusion model tutorial - Nikolay Malkin (University of Edinburgh
 )
DTSTART:20250623T130000Z
DTEND:20250623T140000Z
UID:TALK232186@talks.cam.ac.uk
DESCRIPTION:This tutorial is an introduction to diffusion models\, a class
  of parametric generative processes that produces samples by iterative loc
 al refinement or denoising. In this tutorial\, we will consider high-dimen
 sional Euclidean spaces\, although variants for discrete spaces and other 
 Riemannian manifolds exist. The exposition will be self-contained assuming
  basic familiarity with latent variable models and principles of deep lear
 ning. I will present the main ideas from the point of view of hierarchical
  variational inference\, with connections mentioned to stochastic differen
 tial equations and annealed Langevin dynamics. The talk will serve as back
 ground for my subsequent talk on diffusion modelling for amortised inferen
 ce\, i.e.\, in the absence of a ground-truth dataset.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR