BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Rianne van den Berg (Microsoft Research Amsterdam)
DTSTART:20220421T160000Z
DTEND:20220421T170000Z
DTSTAMP:20260423T003245Z
UID:MPML/72
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/MPML/72/">Ge
 nerative models for discrete random variables</a>\nby Rianne van den Berg 
 (Microsoft Research Amsterdam) as part of Mathematics\, Physics and Machin
 e Learning (IST\, Lisbon)\n\n\nAbstract\nn this talk I will discuss how di
 fferent classes of generative models can be adapted to handle discrete ran
 dom variables\, and how this can be used to connect generative models to d
 ownstream tasks such as lossless compression. I will start by discussing n
 ormalizing flow models\, and the challenges that arise when converting the
 se models that are typically designed for real-valued random variables to 
 discrete random variables. Next\, I will demonstrate how denoising diffusi
 on models with discrete state spaces have a rich design space in terms of 
 the noising process\, and how this influences the performance of the learn
 ed denoising model. Finally\, I will show how denoising diffusion models c
 an be connected to autoregressive models\, and introduce an autoregressive
  model with a random generation order.\n
LOCATION:https://researchseminars.org/talk/MPML/72/
END:VEVENT
END:VCALENDAR