TITLE: Hard Thresholding–based Methods for Robust Learning

ABSTRACT:

Learning in presence of outliers is a critical problem that can heavily affect performance of the learning algorithms in practice. In this talk, we present a general approach for learning with outliers, where we iteratively estimate the model parameters with estimated inliers and threshold out point which seems unlikely to be generated from the model to obtain more refined set of inliers. We instantiate this general approach for the outlier efficient PCA problem and demonstrate that it leads to nearly optimal solution in O(PCA) computation time.

BIO:

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, non-convex optimization, high-dimensional statistics, and optimization algorithms in general. He also works on applications of machine learning to privacy, computer vision, text mining, and natural language processing.