BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Los_Angeles BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260201T234320Z UID:94F16FEB-C36C-411C-9401-0423ED8296C1 DTSTART;TZID=America/Los_Angeles:20260505T110000 DTEND;TZID=America/Los_Angeles:20260505T120000 DESCRIPTION:Title: Generative AI and Deep Learning for Resource Allocation in 6G Wireless Networks\n\nAbstract:\nThis talk provides an in-depth explo ration of resource management in 6G wireless networks\, focusing on the vi sion\, key performance indicators (KPIs)\, key enabling techniques (KETs)\ , and the diverse array of services characteristic of these advanced netwo rks. The distinct challenges inherent in 6G resource management call for a pivotal shift toward artificial intelligence (AI) and machine learning (M L)–driven solutions\, requiring a departure from traditional optimizatio n-centric approaches.\n\nThe talk sheds light on generative AI and unsuper vised ML strategies tailored to effectively address convex and non-convex resource management optimization problems. A key focus is placed on deep u nsupervised learning techniques for network resource allocation under nonl inear and non-convex constraints. Deep implicit layers and differentiable projection methods are explored as mechanisms to ensure zero constraint vi olations in applications such as beamforming\, phase-shift optimization\, and power allocation.\n\nFurthermore\, the potential of generative AI mode ls\, including large language models (LLMs)\, to enable proactive network resource allocation is examined\, highlighting their role in optimizing pe rformance and reducing reliance on traditional heuristics. The session con cludes by identifying key research gaps and future directions\, paving the way for next-generation AI-driven wireless networks.\n\nCo-sponsored by: Hong-chuan Yang\n\nRoom: 660\, Bldg: Engineering/Computer Science Building (ECS)\, 3800 Finnerty Road\, Victoria\, British Columbia\, Canada\, V8P 5 C2 LOCATION:Room: 660\, Bldg: Engineering/Computer Science Building (ECS)\, 38 00 Finnerty Road\, Victoria\, British Columbia\, Canada\, V8P 5C2 ORGANIZER:cai@uvic.ca SEQUENCE:1 SUMMARY:Generative AI and Deep Learning for Resource Allocation in 6G Wirel ess Networks URL;VALUE=URI:https://events.vtools.ieee.org/m/536434 X-ALT-DESC:Description: <br /><div>\n<p class="x_x_MsoNormal"><strong>Title :</strong>&nbsp\;Generative AI and Deep Learning for Resource Allocation i n 6G Wireless Networks</p>\n</div>\n<div>\n<p class="x_x_MsoNormal"><stron g>Abstract:</strong><br>This talk provides an in-depth exploration of reso urce management in 6G wireless networks\, focusing on the vision\, key per formance indicators (KPIs)\, key enabling techniques (KETs)\, and the dive rse array of services characteristic of these advanced networks. The disti nct challenges inherent in 6G resource management call for a pivotal shift toward artificial intelligence (AI) and machine learning (ML)&ndash\;driv en solutions\, requiring a departure from traditional optimization-centric approaches.</p>\n</div>\n<div>\n<p class="x_x_MsoNormal">The talk sheds l ight on generative AI and unsupervised ML strategies tailored to effective ly address convex and non-convex resource management optimization problems . A key focus is placed on deep unsupervised learning techniques for netwo rk resource allocation under nonlinear and non-convex constraints. Deep im plicit layers and differentiable projection methods are explored as mechan isms to ensure zero constraint violations in applications such as beamform ing\, phase-shift optimization\, and power allocation.</p>\n</div>\n<div>\ n<p class="x_x_MsoNormal">Furthermore\, the potential of generative AI mod els\, including large language models (LLMs)\, to enable proactive network resource allocation is examined\, highlighting their role in optimizing p erformance and reducing reliance on traditional heuristics. The session co ncludes by identifying key research gaps and future directions\, paving th e way for next-generation AI-driven wireless networks.</p>\n</div> END:VEVENT END:VCALENDAR