BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Generative Modeling by Estimating Gradients of the Data Distributi
 on - Stefano Ermon (Stanford University)
DTSTART:20220427T150000Z
DTEND:20220427T160000Z
UID:TALK173486@talks.cam.ac.uk
CONTACT:Randolf Altmeyer
DESCRIPTION:Existing generative models are typically based on explicit rep
 resentations of probability distributions (e.g.\, autoregressive or VAEs) 
 or implicit sampling procedures (e.g.\, GANs). We propose an alternative a
 pproach based on modeling directly the vector field of gradients of the da
 ta distribution (scores). Our framework allows flexible architectures\, re
 quires no sampling during training or the use of adversarial training meth
 ods. Additionally\, score-based generative models enable exact likelihood 
 evaluation through connections with normalizing flows. We produce samples 
 comparable to GANs\, achieving new state-of-the-art inception scores\, and
  competitive likelihoods on image datasets.\n\nJoin Zoom Meeting\nhttps://
 maths-cam-ac-uk.zoom.us/j/94812219444?pwd=K00vZUVUU2NDbHozR2h1UzdLRlI1QT09
 \nMeeting ID: 948 1221 9444\nPasscode: 485548
LOCATION:Virtual (Zoom details under abstract)
END:VEVENT
END:VCALENDAR