BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160553Z
LOCATION:Track 1
DTSTART;TZID=America/New_York:20201112T154000
DTEND;TZID=America/New_York:20201112T161500
UID:submissions.supercomputing.org_SC20_sess207_ws_drbsd103@linklings.com
SUMMARY:Data Compression with Deep Learning Based Generative Modeling
DESCRIPTION:Workshop\n\nData Compression with Deep Learning Based Generati
 ve Modeling\n\nChoi, Pugmire, Klasky\n\nWe have been developing a VAE-base
 d data compression method, called VAe Physics Optimized Reduction (VAPOR),
  with a dataset from XGC, a fusion simulation code. VAPOR is based on Vect
 or Quantized Variational Auto Encoder (VQ-VAE), focusing on compressing XG
 C 5D distribution data as well as preserving physics constraints. Key feat
 ures of VAPOR are three-fold; i) find a reduced representation of physics 
 data, ii) reconstruct the data with a minimum loss, iii) preserve physics 
 information (e.g., mass, energy, moment conservation) .\n\nWe will discuss
  challenges in XGC 5D data reconstruction and present our initial experien
 ces and results on how we construct Deep Neural Network (DNN) for VAPOR to
  optimize the reconstruction quality of XGC 5D data and integrate XGC’s ph
 ysics constraints, and share performance considerations to execute with XG
 C as an in situ process.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR