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:916@fds.yale.edu
DTSTART;TZID=America/New_York:20260422T120000
DTEND;TZID=America/New_York:20260422T130000
DTSTAMP:20260413T170402Z
URL:https://fds.yale.edu/events/fds-colloquium-avrim-blum-ttic/
SUMMARY:FDS Colloquium: Avrim Blum (TTIC)\, "Approximation Guarantees for D
 ata-Driven Algorithm Design"
DESCRIPTION:\nAbstract: Data-Driven Algorithm Design refers to the idea of 
 using typical problem-instances from a domain of interest to help produce 
 an algorithm that performs particularly well on that domain. This idea has
  a long history in AI\, and recently\, there have been growing advances in
  Theoretical Computer Science and Machine Learning Theory developing tools
  for proving guarantees for this approach. In this talk\, I will discuss w
 ork on using ideas from approximation algorithms (and competitive analysis
 ) to simplify the algorithmic challenge involved\, and perhaps also make i
 t easier to compare to stronger benchmarks\, by willingly giving up some c
 onstant (or logarithmic or polynomial) factors. I will focus on the settin
 g of algorithms that can benefit from “warm start” initialization\, wh
 ere we will also see connections to several classic algorithmic problems.\
 n\n\n\nSpeaker Bio: Avrim Blum is Professor and Chief Academic Officer at 
 the Toyota Technological Institute at Chicago (TTIC)\; prior to this he wa
 s on the faculty at Carnegie Mellon University for 25 years. His main rese
 arch interests are in Machine Learning Theory\, Algorithmic Game Theory\, 
 Approximation Algorithms\, and Algorithmic Fairness. He has served as Prog
 ram Chair for the Conference on Learning Theory (COLT)\, the IEEE Symposiu
 m on Foundations of Computer Science (FOCS)\, and the Innovations in Theor
 etical Computer Science Conference (ITCS). Blum is recipient of the AI Jou
 rnal Classic Paper Award\, the ICML/COLT 10-Year Best Paper Award\, the AC
 M Paris Kanellakis Award\, the Sloan Fellowship\, the NSF National Young I
 nvestigator Award\, and the Herbert Simon Teaching Award\, and he is a Fel
 low of the ACM.\n
CATEGORIES:FDS Events,Colloquium
LOCATION:Yale Institute for Foundations of Data Science & Webcast\, 219 Pro
 spect Street\, 13th Floor\, New Haven\, CT\, 06511\, United States
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=219 Prospect Street\, 13th 
 Floor\, New Haven\, CT\, 06511\, United States;X-APPLE-RADIUS=100;X-TITLE=
 Yale Institute for Foundations of Data Science & Webcast: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