BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Eastern BEGIN:DAYLIGHT DTSTART:20220313T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20221106T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20220917T181957Z UID:DE89F44F-5AC0-4181-86AD-533E2459B9B9 DTSTART;TZID=US/Eastern:20220914T120000 DTEND;TZID=US/Eastern:20220914T130000 DESCRIPTION:The massive datasets being compiled by our society present new challenges and opportunities to the field of statistical learning and infe rence. The increasing dimensionality of modern datasets lead to unique geo metric and probabilistic phenomena\, including scaling limits\, phase tran sitions\, and universality. A deeper understanding and clever exploitation of such fascinating (and sometimes counter-intuitive) high-dimensional ph enomena can translate to both theoretical breakthroughs and novel algorith ms.\n\nIn this talk\, I will present several lines of recent work on signa l estimation and multilayer neural networks where such high-dimensional ph enomena are explored and exploited.\n\nCo-sponsored by: Fairleigh Dickinso n University\n\nSpeaker(s): Dr. Yue M. Lu\, \n\nAgenda: \nThe massive data sets being compiled by our society present new challenges and opportunitie s to the field of statistical learning and inference. The increasing dimen sionality of modern datasets lead to unique geometric and probabilistic ph enomena\, including scaling limits\, phase transitions\, and universality. A deeper understanding and clever exploitation of such fascinating (and s ometimes counter-intuitive) high-dimensional phenomena can translate to bo th theoretical breakthroughs and novel algorithms.\n\nIn this talk\, I wil l present several lines of recent work on signal estimation and multilayer neural networks where such high-dimensional phenomena are explored and ex ploited.\n\nRoom: M105\, Bldg: Muscarelle Center\, M105\, \, 1000 River R oad \, Teaneck \, New Jersey\, United States\, 07666\, Virtual: https://ev ents.vtools.ieee.org/m/319524 LOCATION:Room: M105\, Bldg: Muscarelle Center\, M105\, \, 1000 River Road \, Teaneck \, New Jersey\, United States\, 07666\, Virtual: https://events .vtools.ieee.org/m/319524 ORGANIZER:tan@fdu.edu SEQUENCE:3 SUMMARY:Exploring and Exploiting High-dimensional Phenomena in Statistical Learning and Inference URL;VALUE=URI:https://events.vtools.ieee.org/m/319524 X-ALT-DESC:Description: <br /><p>The massive datasets being compiled by our society present new challenges and opportunities to the field of statisti cal learning and inference. The increasing dimensionality of modern datase ts lead to unique geometric and probabilistic phenomena\, including scalin g limits\, phase transitions\, and universality. A deeper understanding an d clever exploitation of such fascinating (and sometimes counter-intuitive ) high-dimensional phenomena can translate to both theoretical breakthroug hs and novel algorithms.</p>\n<p>In this talk\, I will present several lin es of recent work on signal estimation and multilayer neural networks wher e such high-dimensional phenomena are explored and exploited.</p><br /><br />Agenda: <br /><p>The massive datasets being compiled by our society pre sent new challenges and opportunities to the field of statistical learning and inference. The increasing dimensionality of modern datasets lead to u nique geometric and probabilistic phenomena\, including scaling limits\, p hase transitions\, and universality. A deeper understanding and clever exp loitation of such fascinating (and sometimes counter-intuitive) high-dimen sional phenomena can translate to both theoretical breakthroughs and novel algorithms.</p>\n<p>In this talk\, I will present several lines of recent work on signal estimation and multilayer neural networks where such high- dimensional phenomena are explored and exploited.</p> END:VEVENT END:VCALENDAR