BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Seminar @ Cornell Tech: Yaron Singer
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260515T050219Z
UID:tag:localist.com\,2008:EventInstance_4559913
DTSTART;VALUE=DATE:20190515
DESCRIPTION:"Algorithms in the Era of Machine Learning: An Inconvenient Tru
 th"\n\nThe traditional approach in algorithm design assumes that there is 
 an underlying objective that is known to the algorithm designer and the fo
 cus is on efficiently optimizing that objective.  In many applications how
 ever\, the objectives we aim to optimize are not known but rather learned 
 from data.  So what are the guarantees of the algorithms we develop and te
 ach when the input is learned from data?  In this talk we will address thi
 s question and discuss challenges at the intersection of machine learning 
 and algorithms. We will present some stark impossibility results and argue
  for new algorithmic paradigms.\n\n \n\nBio:\n\nYaron Singer is an Associa
 te Professor of Computer Science at Harvard University.  He was previously
  a postdoctoral researcher at Google Research and obtained his PhD from UC
  Berkeley.  He is the recipient of the NSF CAREER award\, the Sloan fellow
 ship\, Facebook faculty award\, Google faculty award\, 2012 Best Student P
 aper Award at the ACM conference on Web Search and Data Mining\, the 2010 
 Facebook Graduate Fellowship\, the 2009 Microsoft Research PhD Fellowship.
GEO:40.755644;-73.956097
LOCATION:Cornell Tech\, Bloomberg Center\, Room TBD
SUMMARY:Seminar @ Cornell Tech: Yaron Singer
URL;VALUE=URI:https://events.cornell.edu/event/seminar_cornell_tech_yaron_s
 inger
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR