Loading Events

« All Events

  • This event has passed.

NLP/ML Colloquium: “Linear Methods for Big Data” – Paramveer Dhillon

April 20 @ 11:00 am - 12:00 pm

Paramveer DhillonNatural Language Processing & Machine Learning Colloquium

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.

Bio:

Paramveer Dhillon is a Posdoctoral Associate at the MIT Sloan School of Management. He is currently working on causal inference for large scale social networks and the internet economy. His general research interests lie in Machine Learning & Statistics with applications to Natural Language Processing, Network Science and Brain Imaging. Paramveer holds an A.M in Statistics and M.S.E & Ph.D in Computer & Information Science all from the University of Pennsylvania. His research has won the Rubinoff Best Dissertation Award, a runner-up best paper award at WISE 2016 and has resulted in several publications at top-tier journals and conferences including JMLR, NIPS, ICML, ACL and EMNLP.

Host: Mohit Bansal

Details

Date:
April 20
Time:
11:00 am - 12:00 pm
Event Categories:
,

Venue

008 Brooks Building (FB008)
Brooks Computer Science Building, S. Columbia St.
Chapel Hill, NC 27599 United States
+ Google Map