Anuj Mahajan works as a Budding Scientist in the Machine Learning and Statistics group. His technical interests include deep learning, reinforcement learning, graphical models, computational learning theory and optimization.
Anuj joined us in July 2016. He has worked on augmenting deep reinforcement learning with symmetry information about the environment and analyzing dynamic pricing policy for public transport systems. Currently, he is working on finding machine learning based solutions for healthcare problems.
Anuj holds a B.Tech+M.Tech (Dual degree) in Computer Science & Engineering from Indian Institute of Technology (IIT) Delhi, where he worked on various problems in probabilistic graphical models. During his time at IIT he created efficient algorithms for inference in Markov logic networks used for statistical relational modeling, proposed graph cut methods for Markov random fields associated with computer vision problems and developed algorithms for feature selection for short text domains using signal processing methods. Some of his work was published in reputed international conferences. Anuj has also helped as an external reviewer for CVPR 2017.
Anuj enjoys playing table tennis, chess and Go. He is also math savvy and likes solving puzzles and reading sci-fi in his free time.
Anuj can be contacted at email@example.com .
- 1. Anuj Mahajan and Theja Tulabandhula. Symmetry detection and exploitation for function approximation in deep RL. In Sixteenth International Conference on Autonomous Agents and Multiagent Sytems. 2017 [AAMAS].
- 2. Happy Mittal, Anuj Mahajan, Vibhav G Gogate, and Parag Singla. Lifted inference rules with constraints. In Advances in Neural Information Processing Systems 28, pages 3501–3509. Curran Associates, Inc., 2015 [NIPS].
- 3. Anuj Mahajan, Sharmistha Jat, and Shourya Roy. Feature selection for short text classification using wavelet packet transform. In Proceedings of the Nineteenth Conference on Computational Natural Language Learning, pages 321–326. Association for Computational Linguistics, 2015 [CoNLL].