Rajsekar Manokaran is an Assistant Professor at the Computer Science and Engineering department at IIT Madras. His research involves viewing the world with an algorithmic lens in order to derive insights.

Professional Experience

• Assistant Professor, CSE, IIT Madras. October, 2014 - now.
• Postdoctoral Researcher, KTH, Stocholm. October 2012 - July 2014.
• Developer at Nouvou Inc., a startup in California - June - August 2012.
• Research Intern, Microsoft Research, India. July - September 2011.
• Research Intern, IBM TJ Watson Lab, NY. May - July 2009.

Education

• PhD in Computer Science and Engineering, Princeton, USA - October 2012.
• B.Tech in Computer Science and Engineering, IIT Madras - August 2006.

Research Interests

Theoretical Machine Learning

Machine Learning is a wide and fast growing field in Computer Science. We are engaged in a theoretical study of models such as RBM and DBNs that are prevalent in Deep Learning networks. Our work aims to understand and improve the training algorithms used there in.

Constraint Satisfaction Problems and Approximability

Constraint Satisfaction Problems or CSPs encapsulate a huge number of real-world optimization problems. The complexity of solving or approximating the optimum of such problems is thus an important object of study.

A common thread in much of my work has been the study of convex relaxations for designing approximation algorithms. This yields results of the following flavour: for a fairly general class of problems, a specific relaxation already yields optimal approximations, upto current algorithmic techniques.