About the Authors
 
Sanjeev Arora
Professor
Princeton University, NJ
arora[ta]princeton[td]edu
http://www.cs.princeton.edu/~arora
Professor
Princeton University, NJ
arora[ta]princeton[td]edu
http://www.cs.princeton.edu/~arora
Sanjeev Arora is Charles C. Fitzmorris Professor of computer science 
at Princeton University. 
He was the founding director and lead PI of the Center for
Computational Intractability. He has received the Goedel prize
twice (as cowinner), for his works on Probabilistically Checkable
Proofs (PCP Theorem) and Approximation Schemes for Geometric
problems such as Euclidean TSP.
 
Elad Hazan 
Assistant Professor
Technion, Israel Institute of Technology
ehazan[ta]ie[td]technion[td]ac[td]il
http://ie.technion.ac.il/~ehazan
Assistant Professor
Technion, Israel Institute of Technology
ehazan[ta]ie[td]technion[td]ac[td]il
http://ie.technion.ac.il/~ehazan
Elad Hazan completed undergraduate studies in  
Tel Aviv  University 
and received  a  Ph.D.  from 
Princeton University in 2006, 
under the supervision of 
Sanjeev Arora. 
From 2006 to 2010 he was a research staff member of the 
Theory Group 
at the 
IBM Almaden Research Center.  
Since 2010, he has been on the faculty at the 
Technion - Israel Institute of Technology.
His research interests focus on  machine learning and convex optimization. 
 
Satyen Kale 
Research Staff Member
IBM Watson Research Center, NY
sckale[ta]us[td]ibm[td]com
http://wwww.satyenkale.com
Research Staff Member
IBM Watson Research Center, NY
sckale[ta]us[td]ibm[td]com
http://wwww.satyenkale.com
Satyen Kale received a B.Tech. degree from 
IIT Bombay 
and a Ph.D. degree from 
Princeton University in 2007. 
His Ph.D. advisor was 
Sanjeev Arora. 
His thesis focused on the topic of this paper: the Multiplicative Weights Update algorithm and its applications. After postdocs at 
Microsoft Research and 
Yahoo! Research, 
he continued his conquest of industrial research labs joining 
IBM Research in 2011. His current research is the design of efficient and practical algorithms for fundamental problems in Machine Learning and Optimization.
