BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20210314T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20201101T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20201204T195940Z
UID:804977B7-0A0C-4AA4-85B5-F7EF38582333
DTSTART;TZID=America/Chicago:20201204T110000
DTEND;TZID=America/Chicago:20201204T121500
DESCRIPTION:Abstract: Modern deep generative models like GANs\, VAEs and in
 vertible flows are achieving amazing results on modeling high-dimensional 
 distributions\, especially for images. We will show how they can be used t
 o solve inverse problems by generalizing compressed sensing beyond sparsit
 y\, extending the theory of Restricted Isometries to sets created by gener
 ative models. We will present the general framework\, new results and open
  problems in this space.\n\nBio: Alex Dimakis is a Professor at the Electr
 ical and Computer Engineering department\, University of Texas at Austin. 
 He received his Ph.D. from UC Berkeley and the Diploma degree from the Nat
 ional Technical University of Athens. He received several awards including
  the IEEE Information Theory Society James Massey Award\, NSF Career\, a G
 oogle research award\, and the Eli Jury dissertation award and the joint I
 EEE Information Theory and Communications Society Best Paper Award. His re
 search interests include information theory\, coding theory and machine le
 arning with a current focus on unsupervised learning.\n\nCo-sponsored by: 
 University of Illinois Chicago -- Electrical and Computer Engineering Depa
 rtment \n\nSpeaker(s): Dr Dimakis\, \n\nChicago\, Illinois\, United States
 \, 60607\, Virtual: https://events.vtools.ieee.org/m/247792
LOCATION:Chicago\, Illinois\, United States\, 60607\, Virtual: https://even
 ts.vtools.ieee.org/m/247792
ORGANIZER:danielat@uic.edu
SEQUENCE:3
SUMMARY:IEEE Chicago's Information Theory Society Webinar: "Deep Generative
  Models and Inverse Problems"
URL;VALUE=URI:https://events.vtools.ieee.org/m/247792
X-ALT-DESC:Description: <br /><p>Abstract: &nbsp\;Modern deep generative mo
 dels like GANs\, VAEs and invertible flows are achieving amazing results o
 n modeling high-dimensional distributions\, especially for images. We will
  show how they can be used to solve inverse problems by generalizing compr
 essed sensing beyond sparsity\, extending the theory of Restricted Isometr
 ies to sets created by generative models. We will present the general fram
 ework\, new results and open problems in this space.<br /><br />Bio: Alex 
 Dimakis is a Professor at the Electrical and Computer Engineering departme
 nt\, University of Texas at Austin. He received his Ph.D. from UC Berkeley
  and the Diploma degree from the National Technical University of Athens. 
 He received several awards including the IEEE Information Theory Society J
 ames Massey Award\, NSF Career\, a Google research award\, and the Eli Jur
 y dissertation award and the joint IEEE Information Theory and Communicati
 ons Society Best Paper Award. His research interests include information t
 heory\, coding theory and machine learning with a current focus on unsuper
 vised learning. &nbsp\;</p>
END:VEVENT
END:VCALENDAR