Kartik Ahuja

“The first principle is that you must not fool yourself and you are the easiest person to fool.”- Richard P. Feynman
alt text 

Kartik Ahuja

AI Resident

IBM Research, Thomas J. Watson Research Center, Yorktown Heights, NY

Google Scholar    Github

Email: ahujak@ucla.edu


I am an AI Resident at IBM Research, Thomas J. Watson Research Center, Yorktown Heights, NY. Before coming to IBM, I completed my PhD in Electrical and Computer Engineering from University of California, Los Angeles and B.tech-M.tech Dual Degree in Electrical Engineering from Indian Institute of Technology, Kanpur.

I work on problems in optimization and game theory with a focus on machine learning. Over the years, I have worked on developing tractable and approximate optimization algorithms for resource allocation problems and different problems in machine learning. More recently, I have been fascinated by problems related to out-of-distribution generalization and robust machine learning algorithms.

Selected Publications and Preprints

  • Kartik Ahuja, Amit Dhurandhar, Karthikeyan Shanmugam, Kush R. Varshney. Learning to Initialize Gradient Descent using Gradient Descent. Submitted.

  • Kartik Ahuja, Mihaela Van der Schaar. Dynamic Matching and Allocation of Tasks. In ACM Transactions on Economics and Computation (TEAC) 7, no. 4 (2019): 1-27 and a short version appeared in 30th International Conference on Game Theory, 2019.

Curriculum Vitae

Here is a link to my CV last updated 18th April, 2020.