Profile picture for user cnarayanan
Dr. Chandra Shekar Lakshminarayanan
Asst. Professor
Email Me


My research areas are reinforcement learning, stochastic control and deep learning.  I obtained my PhD from the Department of Computer Science and Automation, Indian Institute of Science (2016), and was a post-doctoral research fellow at the Department of Computing Science (July 2016- June 2017), University of Alberta, and a research scientist at DeepMind, London (August 2017-July 2018). Prior to my PhD, I was an analog design engineer at Cosmic Circuits, Bangalore for a period of 3 years. I joined IITPKD as an assistant professor on July 2018.


Reinforcement Learning; Stochastic Control; Deep Learning


Artificial Intelligence (course/lab)

Additional Information

Chandrashekar Lakshminarayanan and Amit Vikram Singh, “Neural Path Features and Neural Path Kernel: Understanding the role of gates in deep learning”, NeurIPS, 2020.

Chandrashekar Lakshminarayanan and Csaba Szepesv ́ari, “Linear Stochastic Approximation: How far does constant step size and iterate averaging go?”, AISTATS, 2018.

Chandrashekar Lakshminarayanan, Shalabh Bhatnagar and Csaba Szepesv ́ari, “A Linearly Relaxed Approximate Linear Program for Markov Decision Processes”, IEEE Transactions on Automatic Control, 2018.

Chandrashekar Lakshminarayanan and Shalabh Bhatnagar, “A Stability Criterion for Two Timescale Stochastic Approximation Schemes”, Automatica, 2017.

Sandeep Kumar, Sindhu Padakandla, Chandrashekar Lakshminarayanan, Priyank Parihar, Kanchi Gopinath and Shalabh Bhanagar, “Scalable Performance Tuning of Hadoop MapReduce: A Noisy Gradient Approach”, IEEE CLOUD (10th International Conference on Cloud Com- puting), 2017.

Raj Kumar Maity, Chandrashekar Lakshminarayanan, Sindhu Padakanla, Shalabh Bhatna- gar, “Shaping Proto-Value Functions Using Rewards”, European Conference on Artificial Intelligence, ECAI, 2016 (extended abstract).

Chandrashekar Lakshminarayanan and Shalabh Bhatnagar, “A Generalized Reduced Linear Program for Markov Decision Processes”, Twenty-Ninth AAAI conference, 2015.

Chandrashekar Lakshminarayanan and Shalabh Bhatnagar, “Approximate Dynamic Pro- gramming with (min, +) linear function approximation for Markov Decision Processes”, 53rd IEEE Annual Conference on Decision and Control (CDC), 2014.

Chandrashekar Lakshminarayanan, Ayush Dubey, Shalabh Bhatnagar and Chithralekha Bal- amurugan, “A Markov Decision Process framework for predictable job completion times on crowd- sourcing platforms”, Proceedings of the Second AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2014 (extended abstract).