BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:874@fds.yale.edu
DTSTART;TZID=America/New_York:20251022T113000
DTEND;TZID=America/New_York:20251022T130000
DTSTAMP:20251016T195926Z
URL:https://fds.yale.edu/events/fds-colloquium-mike-winer-ias/
SUMMARY:FDS Colloquium: Mike Winer (IAS)\, "Heuristic Estimation of Neural 
 Network Outputs"
DESCRIPTION:\nTalk summary: Given a neural network and a description of its
  input distribution\, what can we say about the outputs? In some sense we 
 have all the information\, but even estimating something like the frequenc
 y of a given rare token might require many forward passes. In this talk I 
 discuss approximate techniques for answering these questions\, often in ma
 nners much more computationally efficient than blindly producing forward p
 asses. I discuss how these techniques shed light not only on what neural n
 etworks do on a given input\, but why they do it.\n\n\n\nSpeaker bio: Mich
 ael Winer is a statistical physicist who studies disordered systems\, thei
 r phase transitions\, thermodynamics\, and dynamics. Much of his work focu
 ses on the physics of glasses and how it connects to broader questions in 
 holography\, deep learning\, and the emergence of complex behavior from si
 mple components. He is interested in how systems of many simple parts can 
 organize into phenomena such as magnets\, glasses\, or intelligence. Micha
 el currently divides his time between the Institute for Advanced Study in 
 Princeton and the Alignment Research Center in Berkeley.\n
CATEGORIES:Fellows Events,FDS Events,Colloquium
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:20250309T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR