Sanjeev Arora works on theoretical computer science and theoretical machine learning. He received a bachelor’s degree in Mathematics with Computer Science from MIT in 1990 and a PhD in Computer Science from Berkeley in 1994. His dissertation on the PCP Theorem was a co-winner of the ACM Doctoral Dissertation prize. In 1994 he joined Princeton University as a faculty member, where he is now Charles C. Fitzmorris Professor of Computer Science. He is currently also Visiting Professor in Mathematics at the Institute for Advanced Study. He has received the Packard Fellowship (1997), Simons Investigator Award (2012), Gödel Prize (2001 and 2010), ACM Prize in Computing (formerly the ACM-Infosys Foundation Award in the Computing Sciences) (2012), and the Fulkerson Prize in Discrete Math (2012). He is a fellow of the American Academy of Arts and Sciences and member of the National Academy of Science.

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.

Membership Type


Election Year


Primary Section

Section 34: Computer and Information Sciences

Secondary Section

Section 11: Mathematics