BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.0.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:967@fds.yale.edu
DTSTART;TZID=America/New_York:20260914T153000
DTEND;TZID=America/New_York:20260914T170000
DTSTAMP:20260914T141240Z
URL:https://fds.yale.edu/events/sds-seminar-elchanan-mossel-mit/
SUMMARY:S&amp\;DS Seminar: Elchanan Mossel (MIT)
DESCRIPTION:\nAbstract: Deep learning challenges much of the traditional th
 inking in statistics and machine learning\, in particular the assumption t
 hat data is i.i.d. from families of distributions that are easy to describ
 e. In the first (more scientific) part of the talk I will review some mode
 ls of hierarchical or correlated data that may explain the need for depth 
 and the efficiency of gradient based methods. In the second (more philosop
 hical) part of the talk I will discuss the importance of data in assessing
  the extent to which the extraordinary performance of LLMs may be explaine
 d by novel reasoning versus plagiarism.\n\n\n
CATEGORIES:Fellows Events,FDS Events,Statistics & Data Science Seminar
LOCATION:Yale Institute for Foundations of Data Science\, Kline Tower 13th 
 Floor\, Room 1327\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=Kline Tower 13th Floor\, Ro
 om 1327\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITL
 E=Yale Institute for Foundations of Data Science:geo:0,0
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR