BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Chicago
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:CDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251101T020626Z
UID:419F6B4C-7C75-46B9-B7F2-DAA339D8B8BA
DTSTART;TZID=America/Chicago:20251105T170000
DTEND;TZID=America/Chicago:20251105T180000
DESCRIPTION:Join us for an engaging presentation on cutting-edge research a
 t the intersection of artificial intelligence and high-performance computi
 ng infrastructure. PhD candidate Kyrian Chinemeze Adimora will present AIM
 S (Adaptive Intelligent Multi-Objective Scheduler)\, a novel machine learn
 ing framework that optimizes supercomputer resource allocation.\n\nWhat Yo
 u&#39;ll Learn:\n\nModern supercomputers and AI datacenters face critical chal
 lenges in managing thousands of concurrent jobs across heterogeneous hardw
 are resources (CPUs\, GPUs\, FPGAs). Traditional scheduling approaches opt
 imize for single objectives (typically throughput)\, leading to significan
 t energy waste\, underutilized resources\, and reduced system reliability.
  AIMS addresses these limitations through an innovative multi-objective op
 timization framework that simultaneously balances performance\, energy eff
 iciency\, and system resilience.\n\nWho Should Attend:\n\nThis presentatio
 n is designed for a broad audience with varying technical backgrounds:\n\n
 - AI/ML enthusiasts interested in reinforcement learning\, graph neural ne
 tworks\, and applied machine learning\n- Computer science students explori
 ng systems research\, distributed computing\, and infrastructure optimizat
 ion\n- Engineering students curious about sustainable computing and energy
 -efficient system design\n- Aspiring researchers considering graduate stud
 ies in AI\, HPC\, or related fields\n- Industry-minded students interested
  in datacenter operations\, cloud computing\, and enterprise-scale resourc
 e management\n\nNo prior expertise in HPC is required\, the presentation u
 ses intuitive analogies and visual explanations to make complex concepts a
 ccessible while providing technical depth for advanced students.\n\nSpeake
 r Bio:\n\nKyrian Chinemeze Adimora is a Third-year PhD candidate in Electr
 ical Engineering and Computer Science at the University of Kansas\, advise
 d by Dr. Hongyang Sun and currently serving as the region 5 IEEE Kansas Ci
 ty Section Educational Activities Chair. His research focuses on applying 
 machine learning techniques to optimize large-scale computing infrastructu
 re. He has published at premier venues including SC ( The International Co
 nference for High Performance Computing\, Networking\, Storage\, and Analy
 sis)\, IEEE TPDS (IEEE Transactions on Parallel and Distributed Systems) a
 nd collaborates with Argonne National Laboratory. His work bridges theoret
 ical machine learning advances with practical systems deployment\, aiming 
 to make computing infrastructure smarter\, greener\, and more efficient.\n
 \nCo-sponsored by: University of Kansas  AI Club\n\nAgenda: \nAGENDA\n\n5:
 00 PM - 5:05 PM\nWelcome &amp; Introductions\n\n- KU AI Club president welcome
 s attendees\n- Brief overview of AI Student Branch activities\n- Presenter
  introduction\n\n5:05 PM - 5:10 PM\nOpening: The HPC Scheduling Crisis\n\n
 - Scale of modern supercomputing challenges\n- Motivation: Why this resear
 ch matters\n- Pizza analogy: Making the problem relatable\n\n5:10 PM - 5:2
 5 PM\nThe AIMS Solution Framework\n\n- Three fundamental problems AIMS add
 resses\n- Architecture overview: GNN + RL + Uncertainty Quantification\n- 
 Graph neural networks: Understanding system relationships\n- Reinforcement
  learning: Learning from experience\n- Multi-objective optimization: Balan
 cing competing goals\n\n5:25 PM - 5:40 PM\nResults &amp; Real-World Impact\n\n
 5:40 PM - 5:45 PM\nBroader Impact &amp; Future Directions\n\n- Applicability t
 o cloud computing and AI datacenters\n- Publications and ongoing research\
 n- Future work: Exascale scaling\, production deployment\n- Career opportu
 nities in HPC and infrastructure research\n\n5:45 PM - 6:00 PM\nInteractiv
 e Q&amp;A Session\n\n- Audience questions (technical and career-focused welcom
 e)\n- Discussion of implementation details\n\nPost-Event:\n\n- Slides and 
 recording distributed via email\n- Survey link for feedback\n- Follow-up r
 esources and reading materials\n\nRoom: 3151\, Bldg: School of Engineering
 \, Learned Hall\, University of Kansas\, School of Engineering\, Learned H
 all\, Lawrence\, Kansas\, United States\, 66045\, Virtual: https://events.
 vtools.ieee.org/m/511042
LOCATION:Room: 3151\, Bldg: School of Engineering\, Learned Hall\, Universi
 ty of Kansas\, School of Engineering\, Learned Hall\, Lawrence\, Kansas\, 
 United States\, 66045\, Virtual: https://events.vtools.ieee.org/m/511042
ORGANIZER:kyrimanjero@gmail.com
SEQUENCE:357
SUMMARY:AIMS: Adaptive Intelligent Multi-Objective Scheduler
URL;VALUE=URI:https://events.vtools.ieee.org/m/511042
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;whitespace-normal break-words&quot;&gt;Join
  us for an engaging presentation on cutting-edge research at the intersect
 ion of artificial intelligence and high-performance computing infrastructu
 re. PhD candidate Kyrian Chinemeze Adimora will present AIMS (Adaptive Int
 elligent Multi-Objective Scheduler)\, a novel machine learning framework t
 hat optimizes supercomputer resource allocation.&lt;/p&gt;\n&lt;p class=&quot;whitespace
 -normal break-words&quot;&gt;&lt;strong&gt;What You&#39;ll Learn:&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;wh
 itespace-normal break-words&quot;&gt;Modern supercomputers and AI datacenters face
  critical challenges in managing thousands of concurrent jobs across heter
 ogeneous hardware resources (CPUs\, GPUs\, FPGAs). Traditional scheduling 
 approaches optimize for single objectives (typically throughput)\, leading
  to significant energy waste\, underutilized resources\, and reduced syste
 m reliability. AIMS addresses these limitations through an innovative mult
 i-objective optimization framework that simultaneously balances performanc
 e\, energy efficiency\, and system resilience.&lt;/p&gt;\n&lt;p class=&quot;whitespace-n
 ormal break-words&quot;&gt;&lt;strong&gt;Who Should Attend:&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;whit
 espace-normal break-words&quot;&gt;This presentation is designed for a broad audie
 nce with varying technical backgrounds:&lt;/p&gt;\n&lt;ul class=&quot;[&amp;amp\;:not(:last-
 child)_ul]:pb-1 [&amp;amp\;:not(:last-child)_ol]:pb-1 list-disc space-y-2.5 pl
 -7&quot;&gt;\n&lt;li class=&quot;whitespace-normal break-words&quot;&gt;&lt;strong&gt;AI/ML enthusiasts&lt;
 /strong&gt; interested in reinforcement learning\, graph neural networks\, an
 d applied machine learning&lt;/li&gt;\n&lt;li class=&quot;whitespace-normal break-words&quot;
 &gt;&lt;strong&gt;Computer science students&lt;/strong&gt; exploring systems research\, d
 istributed computing\, and infrastructure optimization&lt;/li&gt;\n&lt;li class=&quot;wh
 itespace-normal break-words&quot;&gt;&lt;strong&gt;Engineering students&lt;/strong&gt; curious
  about sustainable computing and energy-efficient system design&lt;/li&gt;\n&lt;li 
 class=&quot;whitespace-normal break-words&quot;&gt;&lt;strong&gt;Aspiring researchers&lt;/strong
 &gt; considering graduate studies in AI\, HPC\, or related fields&lt;/li&gt;\n&lt;li c
 lass=&quot;whitespace-normal break-words&quot;&gt;&lt;strong&gt;Industry-minded students&lt;/str
 ong&gt; interested in datacenter operations\, cloud computing\, and enterpris
 e-scale resource management&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p class=&quot;whitespace-normal break
 -words&quot;&gt;No prior expertise in HPC is required\, the presentation uses intu
 itive analogies and visual explanations to make complex concepts accessibl
 e while providing technical depth for advanced students.&lt;/p&gt;\n&lt;p class=&quot;wh
 itespace-normal break-words&quot;&gt;&lt;strong&gt;Speaker Bio:&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;
 whitespace-normal break-words&quot;&gt;Kyrian Chinemeze Adimora is a Third-year Ph
 D candidate in Electrical Engineering and Computer Science at the Universi
 ty of Kansas\, advised by Dr. Hongyang Sun and currently serving as the re
 gion 5 IEEE Kansas City Section Educational Activities Chair. His research
  focuses on applying machine learning techniques to optimize large-scale c
 omputing infrastructure. He has published at premier venues including SC (
  The International Conference for High Performance Computing\, Networking\
 , Storage\, and Analysis)\, IEEE TPDS (IEEE Transactions on Parallel and D
 istributed Systems) and collaborates with Argonne National Laboratory. His
  work bridges theoretical machine learning advances with practical systems
  deployment\, aiming to make computing infrastructure smarter\, greener\, 
 and more efficient.&lt;/p&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;p class=&quot;MsoNormal&quot;&gt;&lt;str
 ong&gt;AGENDA&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;5:00 PM - 5:05 PM&lt;/s
 trong&gt;&lt;br&gt;Welcome &amp;amp\; Introductions&lt;/p&gt;\n&lt;ul style=&quot;margin-top: 0in\;&quot; 
 type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l0 level1 lfo1\; tab-
 stops: list .5in\;&quot;&gt;KU AI Club president welcomes attendees&lt;/li&gt;\n&lt;li clas
 s=&quot;MsoNormal&quot; style=&quot;mso-list: l0 level1 lfo1\; tab-stops: list .5in\;&quot;&gt;Br
 ief overview of AI Student Branch activities&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot; s
 tyle=&quot;mso-list: l0 level1 lfo1\; tab-stops: list .5in\;&quot;&gt;Presenter introdu
 ction&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;5:05 PM - 5:10 PM&lt;/strong&gt;
 &lt;br&gt;Opening: The HPC Scheduling Crisis&lt;/p&gt;\n&lt;ul style=&quot;margin-top: 0in\;&quot; 
 type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l1 level1 lfo2\; tab-
 stops: list .5in\;&quot;&gt;Scale of modern supercomputing challenges&lt;/li&gt;\n&lt;li cl
 ass=&quot;MsoNormal&quot; style=&quot;mso-list: l1 level1 lfo2\; tab-stops: list .5in\;&quot;&gt;
 Motivation: Why this research matters&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;m
 so-list: l1 level1 lfo2\; tab-stops: list .5in\;&quot;&gt;Pizza analogy: Making th
 e problem relatable&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;5:10 PM - 5:
 25 PM&lt;/strong&gt;&lt;br&gt;The AIMS Solution Framework&lt;/p&gt;\n&lt;ul style=&quot;margin-top: 
 0in\;&quot; type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l5 level1 lfo3
 \; tab-stops: list .5in\;&quot;&gt;Three fundamental problems AIMS addresses&lt;/li&gt;\
 n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l5 level1 lfo3\; tab-stops: list .
 5in\;&quot;&gt;Architecture overview: GNN + RL + Uncertainty Quantification&lt;/li&gt;\n
 &lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l5 level1 lfo3\; tab-stops: list .5
 in\;&quot;&gt;Graph neural networks: Understanding system relationships&lt;/li&gt;\n&lt;li 
 class=&quot;MsoNormal&quot; style=&quot;mso-list: l5 level1 lfo3\; tab-stops: list .5in\;
 &quot;&gt;Reinforcement learning: Learning from experience&lt;/li&gt;\n&lt;li class=&quot;MsoNor
 mal&quot; style=&quot;mso-list: l5 level1 lfo3\; tab-stops: list .5in\;&quot;&gt;Multi-objec
 tive optimization: Balancing competing goals&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p class=&quot;MsoNor
 mal&quot;&gt;&lt;strong&gt;5:25 PM - 5:40 PM&lt;/strong&gt;&lt;br&gt;Results &amp;amp\; Real-World Impac
 t&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;5:40 PM - 5:45 PM&lt;/strong&gt;&lt;br&gt;Broader 
 Impact &amp;amp\; Future Directions&lt;/p&gt;\n&lt;ul style=&quot;margin-top: 0in\;&quot; type=&quot;d
 isc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l2 level1 lfo4\; tab-stops: 
 list .5in\;&quot;&gt;Applicability to cloud computing and AI datacenters&lt;/li&gt;\n&lt;li
  class=&quot;MsoNormal&quot; style=&quot;mso-list: l2 level1 lfo4\; tab-stops: list .5in\
 ;&quot;&gt;Publications and ongoing research&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;ms
 o-list: l2 level1 lfo4\; tab-stops: list .5in\;&quot;&gt;Future work: Exascale sca
 ling\, production deployment&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: 
 l2 level1 lfo4\; tab-stops: list .5in\;&quot;&gt;Career opportunities in HPC and i
 nfrastructure research&lt;/li&gt;\n&lt;/ul&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;5:45 PM -
  6:00 PM&lt;/strong&gt;&lt;br&gt;Interactive Q&amp;amp\;A Session&lt;/p&gt;\n&lt;ul style=&quot;margin-t
 op: 0in\;&quot; type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l3 level1 
 lfo5\; tab-stops: list .5in\;&quot;&gt;Audience questions (technical and career-fo
 cused welcome)&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l3 level1 lfo5
 \; tab-stops: list .5in\;&quot;&gt;Discussion of implementation details&lt;/li&gt;\n&lt;/ul
 &gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;Post-Event:&lt;/strong&gt;&lt;/p&gt;\n&lt;ul style=&quot;margi
 n-top: 0in\;&quot; type=&quot;disc&quot;&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l4 leve
 l1 lfo6\; tab-stops: list .5in\;&quot;&gt;Slides and recording distributed via ema
 il&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot; style=&quot;mso-list: l4 level1 lfo6\; tab-stops
 : list .5in\;&quot;&gt;Survey link for feedback&lt;/li&gt;\n&lt;li class=&quot;MsoNormal&quot; style=
 &quot;mso-list: l4 level1 lfo6\; tab-stops: list .5in\;&quot;&gt;Follow-up resources an
 d reading materials&lt;/li&gt;\n&lt;/ul&gt;
END:VEVENT
END:VCALENDAR