Paramveer Dhillon (MIT) presents Linear Methods for Big Data

Title: Linear Methods for Big Data

Abstract:

Statistical Machine Learning has seen great advances in the last decade owing to the availability of large-scale annotated datasets and significant improvements in computation hardware. Amidst this measurement revolution, it has become increasingly important to come up with statistical methods that are not only statistically efficient but that are also computationally efficient i.e. they run fast. 

Drawing on these developments and recent advances in random matrix theory, I will present my work on building fast and theoretically sound methods for linear regression (OLS) and canonical correlation analysis (CCA). I will also describe how these methods can be used to generate linear features that give a state-of-the-art performance on several natural language processing tasks.