BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: What Your AI Does Not Know
DTSTART:20210325T140000
DTEND:20210325T150000
DTSTAMP:20260407T041019Z
UID:5d91575d2bfb32be33b9d0c87e9f2909176e7482097472e1615eb121
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Christos Tzamos - University of Wisconsin-Madison\n\nAbstr
 act\nAs Machine Learning is entering our lives\, we are increasingly trust
 ing many important decisions to computer systems. To create reliable and t
 rustworthy technology\, computer science must address many outstanding cha
 llenges\, integrating concepts and ideas from statistics and the social sc
 iences.\n\nIn this talk\, I will present several contributions of my resea
 rch\, expanding the frontier of computer science to address complexities t
 hat arise in modern machine learning applications. In particular\, I will 
 show how to adapt influential ideas from statistics to create efficient al
 gorithms that deal with inputs that are biased or unreliable. Adapting ide
 as from Economics\, I will show how to design systems that are robust to s
 trategic behavior of their users.\n\nBio\nChristos Tzamos is an Assistant 
 Professor in the Department of Computer Sciences at University of Wisconsi
 n-Madison and a member of the Theory of Computing group. His research inte
 rests lie in the interface of Theory of Computation with Economics and Gam
 e Theory\, Machine Learning\, Statistics and Probability Theory. He comple
 ted his PhD in the Theory of Computation group of MIT advised by Costis Da
 skalakis. He studied Electrical and Computer Engineering at NTUA before hi
 s PhD\, and afterwards he was a postdoctoral researcher at Microsoft Resea
 rch (New England) working on Mechanism Design\, Algorithms and Machine Lea
 rning. He is the recipient of a Simons Foundation award\, the George M. Sp
 rowls award\, the best paper and the best student paper award in EC 2013 a
 nd of an outstanding paper award in NeurIPS 2019.\n\nMore information
LOCATION:https://epfl.zoom.us/j/87853672441?pwd=aXNyalp1Q2ZENmNlci83QVFtaG
 FXQT09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR
