BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000713Z
LOCATION:505
DTSTART;TZID=America/Denver:20231113T140900
DTEND;TZID=America/Denver:20231113T141200
UID:submissions.supercomputing.org_SC23_sess442_ws_whpc104@linklings.com
SUMMARY:An Analysis of Change Point Detection in High Performance Computin
 g
DESCRIPTION:Vijayalakshmi Saravanan (University of South Dakota)\n\nAs hig
 h-performance computing approaches the exascale era, the analysis of the v
 ast amount of monitoring data generated by supercomputers has become incre
 asingly challenging for data analysts. The detection of change points, whi
 ch plays a critical role in anomaly detection, performance optimization, a
 nd root cause analysis of problems and failures, has grown beyond human ca
 pacity for manual review. To address this issue, our focus lies in develop
 ing an effective model capable of identifying anomalous behavior, and to a
 chieve this, we introduce the concept of an online adaptive sampling algor
 ithm. By evaluating the model's performance across various use cases, we c
 onduct tests on a complex datasets to detect change points.  Overall, we o
 bserve that the model successfully captures key features of normal behavio
 r, and we believe it opens promising avenues for further research, particu
 larly in assisting with various tasks related to anomaly detection and per
 formance optimization in high-performance computing environments.\n\nTag: 
 State of the Practice\n\nRegistration Category: Workshop Reg Pass\n\nSessi
 on Chairs: Elsa J. Gonsiorowski (Lawrence Livermore National Laboratory (L
 LNL)) and Mozhgan Kabiri chimeh (NVIDIA Corporation)\n\n
END:VEVENT
END:VCALENDAR