BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250422T205206Z UID:C627FBAC-748E-4C31-B4DF-0A31CF5624EE DTSTART;TZID=America/New_York:20250417T180000 DTEND;TZID=America/New_York:20250417T220000 DESCRIPTION:Abstract\nFog learning is an emerging paradigm for optimizing t he orchestration of artificial intelligence services over contemporary net work systems. Different from existing distributed techniques such as feder ated learning\, fog learning emphasizes intrinsically in its design the un ique node\, network\, and data properties encountered in today’s fog net works that span computing elements from the edge to the cloud. An importan t thread of research in fog learning has been on understanding the role th at local topologies formed on an ad-hoc basis among proximal groups of het erogeneous computing elements can play in elevating the achievable tradeof f between intelligence quality and resource efficiency. In this talk\, I w ill discuss recent results on the analysis of fog learning processes which give insights into the impact that these topologies\, along with other pr operties such as model characteristics and fog decision parameters\, have on global training performance. Additionally\, I will discuss the developm ent of adaptive control methodologies that leverage such relationships for jointly optimizing relevant fog learning metrics.\n\nDistinguished Lectur er Series: https://www.comsoc.org/membership/distinguished-lecturers\nSpea ker: https://www.comsoc.org/christopher-greg-brinton\n\nQuestions about th e venue on April 17\, please reach out to: Yiling Li\, yl4841@princeton.ed u\n\nCo-sponsored by: Princeton / Central Jersey Section\n\nSpeaker(s): Ch ris Brinton\, \n\nAgenda: \n6:30-7:00pm Gather\, Refreshments and Introduc tion\n7:00-8:00pm Lecture\n8:00-8:30pm Q&A\, networking\, wrap-up\n\nRoom: 104\, Bldg: Computer Science Building\, 35 Olden St\, Princeton\, New Jer sey\, United States\, 08540 LOCATION:Room: 104\, Bldg: Computer Science Building\, 35 Olden St\, Prince ton\, New Jersey\, United States\, 08540 ORGANIZER:fran_oconnell@fxoinc.com SEQUENCE:36 SUMMARY:From Federated to Fog Learning: Expanding the Frontier of Model Tra ining over Contemporary Wireless Network Systems URL;VALUE=URI:https://events.vtools.ieee.org/m/480827 X-ALT-DESC:Description: <br /><p>Abstract<br>Fog learning is an emerging pa radigm for optimizing the orchestration of artificial intelligence service s over contemporary network systems. Different from existing distributed t echniques such as federated learning\, fog learning emphasizes intrinsical ly in its design the unique node\, network\, and data properties encounter ed in today&rsquo\;s fog networks that span computing elements from the ed ge to the cloud. An important thread of research in fog learning has been on understanding the role that local topologies formed on an ad-hoc basis among proximal groups of heterogeneous computing elements can play in elev ating the achievable tradeoff between intelligence quality and resource ef ficiency. In this talk\, I will discuss recent results on the analysis of fog learning processes which give insights into the impact that these topo logies\, along with other properties such as model characteristics and fog decision parameters\, have on global training performance. Additionally\, I will discuss the development of adaptive control methodologies that lev erage such relationships for jointly optimizing relevant fog learning metr ics.</p>\n<p>Distinguished Lecturer Series:&nbsp\;<a href="https://www.com soc.org/membership/distinguished-lecturers">https://www.comsoc.org/members hip/distinguished-lecturers</a><br>Speaker: https://www.comsoc.org/christo pher-greg-brinton</p>\n<p>&nbsp\;</p>\n<p>Questions about the venue on Apr il 17\, please reach out to: Yiling Li\,&nbsp\; <a href="mailto:yl4841@pri nceton.edu" target="_blank" rel="noopener">yl4841@princeton.edu</a></p><br /><br />Agenda: <br /><p>6:30-7:00pm&nbsp\; Gather\, Refreshments and Int roduction<br>7:00-8:00pm&nbsp\; Lecture<br>8:00-8:30pm&nbsp\; Q&amp\;A\, n etworking\, wrap-up</p> END:VEVENT END:VCALENDAR