Data Aware Models and Algorithms for Machine Learning
Presented by Pranjal Awasthi, Princeton University

Pranjal's Abstract:
---------------
Algorithms research has traditionally been problem centric, with an emphasis on rigorous guarantees for worst case instances. This approach however, often leads to pessimistic predictions that do not accurately reflect the nature of real life instances.

With the availability of data at a large scale across numerous domains, comes a golden opportunity. The aim is to develop new frameworks and algorithms for machine learning that can use the nature of data to gain a more fine grained understanding of the problem at hand. I call this as data aware modeling.

I will showcase how data aware models and algorithms can lead to new insights into various different problems in machine learning. In particular, I will present specific examples involving classical problems such as k-means and spectral clustering, and more modern applications in semi-supervised and interactive learning.

Speaker Bio: Pranjal Awasthi is a Postdoctoral researcher in the computer science department at Princeton University. He obtained his PhD in 2013 in the machine learning department at Carnegie Mellon University. His research is in algorithms for problems arising in machine learning. He is interested in designing new models for modern learning tasks, and algorithms with optimal guarantees on realistic instances. His work has won a best student paper award at COLT 2013.