BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:An Overview of Normalizing Flows - Robert Pinsler
DTSTART:20190424T130000Z
DTEND:20190424T143000Z
UID:TALK123772@talks.cam.ac.uk
CONTACT:Robert Pinsler
DESCRIPTION:Normalizing flows have become extremely popular of late due to
  them having high capacity *and* supporting exact density evaluation.   Th
 is has made flows a state-of-the-art tool for variational inference and ge
 nerative modeling\, with DeepMind's WaveNet being the most notable success
  story.  In turn\, the research literature has been inundated with flow va
 riants\, making it hard to extract trends in this subfield.  In this meeti
 ng of the reading group\, we attempt to organize the recent developments i
 n normalizing flows.  Beginning with discrete flows\, we describe how earl
 y models such as NICE have been gradually endowed with more capacity\, res
 ulting in SOTA generators such as OpenAI's Glow.  We also summarize the va
 rious masking procedures essential to defining autoregressive flows\, incl
 uding Parallel WaveNet.  Lastly\, we highlight the burgeoning field of con
 tinuous-time flows and numerical methods for their training and evaluation
 .
LOCATION:Engineering Department\, CBL Room BE-438
END:VEVENT
END:VCALENDAR