Proceedings of the National Academy of Sciences of the United States of America

About the PNAS Member Editor
Name Arora, Sanjeev
Location Princeton University
Primary Field Computer and Information Sciences
Secondary Field Mathematics
 Election Citation
Arora is the most influential and innovative theoretical computer scientist under 50. He has revolutionized large research areas and created new ones with new questions, definitions, techniques and results. These include optimization algorithms, probabilistic interactive proofs, hardness of approximation and coding theory.
 Research Interests
Sanjeev Arora is currently interested in developing fundamental, mathematical understanding of today's machine learning methods. We do not understand when or why training succeeds, in how much time and using what number of training examples. We would like to do machine learning with fewer training examples, or be able to transfer learning from one dataset to a related dataset. Most of these questions are wide open from a mathematical viewpoint, and his group is working on understanding the dynamics of optimization algorithms, generalization, generative models, tensor decomposition methods, theory of semantics and natural language processing, etc. They also work on applying machine learning insights to help discovery in social science and neuroscience.

 
These pages are for the use of PNAS Editorial Board members and authors searching for PNAS member editors. For information about the National Academy of Sciences or its membership, please see http://www.nasonline.org.
National Academy of Sciences | Copyright ©2019, All Rights Reserved