BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T054800Z
LOCATION:240-241-242
DTSTART;TZID=America/Chicago:20211116T143000
DTEND;TZID=America/Chicago:20211116T150000
UID:submissions.supercomputing.org_SC21_sess150_pap460@linklings.com
SUMMARY:AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search
  with Autotuned Data-Parallel Training for Tabular Data
DESCRIPTION:Paper\n\nAgEBO-Tabular: Joint Neural Architecture and Hyperpar
 ameter Search with Autotuned Data-Parallel Training for Tabular Data\n\nEg
 ele, Balaprakash, Guyon, Vishwanath, Xia...\n\nDeveloping high-performing 
 predictive models for large tabular data sets is a challenging task. Neura
 l architecture search (NAS) is an AutoML approach that generates and evalu
 ates multiple neural networks (NNs) with different architectures concurren
 tly to automatically discover a high-performing model. A key issue in NAS,
  particularly for large data sets, is the large computation time required 
 to evaluate each generated architecture. While data-parallel training has 
 the potential to address this issue, a straightforward approach can result
  in significant loss of accuracy. To that end, we develop AgEBO-Tabular, w
 hich combines Aging Evolution (AE) to search over neural architectures and
  asynchronous Bayesian optimization (BO) to search over hyperparameters to
  adapt data-parallel training. We evaluate the efficacy of our approach on
  the ECP-Candle Benchmarks.\n\nTag: Reproducibility Badge, Algorithms, App
 lications, Performance\n\nRegistration Category: Tech Program Reg Pass\n\n
 Reproducibility Badges: Artifact Available
END:VEVENT
END:VCALENDAR