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:20250626T234543Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241119T120000
DTEND;TZID=America/New_York:20241119T170000
UID:submissions.supercomputing.org_SC24_sess487_post146@linklings.com
SUMMARY:Development of TEZip in PyTorch: Integrating New Prediction Models
  into an Existing Compression Framework
DESCRIPTION:Akshay Nambudiripad (Columbia University), Amarjit Singh and K
 ento Sato (RIKEN), and Weikuan Yu (Florida State University)\n\nIn high pe
 rformance computing, researchers often work with extremely large time-seri
 es datasets. Compression techniques allow them to shrink their data down, 
 allowing for quicker and less storage-intensive transfers. TEZip is a comp
 ression model that utilizes PredNet (a video prediction model) to predict 
 each frame of a time-series dataset, subtracting these predictions from th
 e actual frames and performing further encoding operations. However, TEZip
  is currently built using TensorFlow and only supports the PredNet model, 
 which trains and predicts slowly. In this work, we rebuilt TEZip in order 
 to accommodate for PyTorch models while also including functionality for P
 redNet as well as ConvLSTM, a simpler time-series prediction model. We fou
 nd that our PyTorch version (specifically with the ConvLSTM model) results
  in faster compression and decompression times. This work is significant i
 n extending the capabilities of TEZip and suggests that simple prediction 
 models are worth exploring in the realm of prediction-based compression.\n
 \nRegistration Category: Tech Program Reg Pass, Exhibits Reg Pass\n\nSessi
 on Chairs: Ayesha Afzal (Friedrich-Alexander University, Erlangen-Nurember
 g; Erlangen National High Performance Computing Center); Sally Ellingson (
 University of Kentucky); and Alan Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR