Prateek Jain

Keynote at ADCOM 2016

Title: Sparse  Linear Regression

Abstract: Sparsity in linear regression is a critical requirement in several important applications like bioinformatics, text processing etc. Sparsity leads to a non-convex optimization problem which has been tackled in a variety of ways in last decade or so. In this talk, I will present a high-level survey of several of these results and also briefly talk about some of our recent results (using non-convex optimization) in this direction.


Prateek Jain is a member of the Machine Learning and Optimization and the Algorithms and Data Sciences Group at Microsoft Research, Bangalore, India. His research interests are in machine learning, statistical learning theory, and optimization algorithms in general and particularly interested in applications of machine learning to privacy, computer vision, text mining and natural language processing. Prateek earned his PhD at the University of Texas at Austin under Prof. Inderjit S. Dhillon.