BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20241103T010000
RDATE:20250309T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20251102T010000
RDATE:20260308T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20261101T010000
RDATE:20270314T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20271107T010000
RDATE:20280312T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:STANDARD
DTSTART:20281105T010000
RDATE:20290311T030000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:America/New_York EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20241007T104500
RDATE:20241103T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20250309T030000
RDATE:20251102T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20260308T030000
RDATE:20261101T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20270314T030000
RDATE:20271107T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20280312T030000
RDATE:20281105T010000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:America/New_York EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:aa239ae9953bf303968ae4baa4292b1d
CATEGORIES:Mathematical Physics Seminar
CREATED:20250925T222055
SUMMARY:Webinar: Andrea Montanari -  Overparameterized Systems: From Smale 17th problem to neutral networks
LOCATION:Zoom
DESCRIPTION:Andrea Montanari  – Stanford University \n \nWednesday, October 8th, 2025\n
 Zoom opens: 10:30AM DST\nSeminar begins: 10:45AM DST\n Overparameterized Sy
 stems: From Smale 17th problem to neutral networks\nSpin glass theory studi
 es the structure of sublevel sets and minima (or near-minima) of certain cl
 asses of random functions in high dimension.  Near-minima of random functio
 ns also play an important role in\nhigh-dimensional statistics and machine 
 learning, where minimizing an empirical risk function is the method of choi
 ce for learning a statistical model  from noisy data.\nI will review some s
 urprising empirical phenomena in modern machine learning, focusing in parti
 cular on overfitting and generalization. I will explain how tools from spin
  glasses and random matrix theory can be used to characterize these phenome
 na in simple models, and clarify them.\n[Based on joint works with Kiana As
 gari, Basil Saeed, Eliran Subag, Pierfrancesco Urbani]\n
X-ALT-DESC;FMTTYPE=text/html:<p style="text-align: center;"><strong>Andrea Montanari&nbsp; – Stanford Un
 iversity </strong></p><p style="text-align: center;"><strong>&nbsp;</strong
 ></p><p style="text-align: center;"><strong>Wednesday,&nbsp;October 8th,&nb
 sp;2025</strong></p><p style="text-align: center;"><strong>Zoom opens: 10:3
 0AM DST</strong></p><p style="text-align: center;"><strong>Seminar begins: 
 10:45AM DST</strong></p><p style="text-align: center;"><strong>&nbsp;<stron
 g>Overparameterized Systems: From Smale 17th problem to neutral networks</s
 trong></strong></p><p>Spin glass theory studies the structure of sublevel s
 ets and minima (or near-minima) of certain classes of random functions in h
 igh dimension. &nbsp;Near-minima of random functions also play an important
  role in</p><p>high-dimensional statistics and machine learning, where mini
 mizing an empirical risk function is the method of choice for learning a st
 atistical model &nbsp;from noisy data.</p><p>I will review some surprising 
 empirical phenomena in modern machine learning, focusing in particular on o
 verfitting and generalization. I will explain how tools from spin glasses a
 nd random matrix theory can be used to characterize these phenomena in simp
 le models, and clarify them.</p><p>[Based on joint works with Kiana Asgari,
  Basil Saeed, Eliran Subag, Pierfrancesco Urbani]</p>
CONTACT:Andrea Montanari
DTSTAMP:20260830T130048
DTSTART;TZID=America/New_York:20251008T104500
DTEND;TZID=America/New_York:20251008T120000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR