AI for Decision Making in Societal Scale Systems
PhD, Degree Pending, Department of Computer Science
Courant Institute of Mathematical Sciences, New York University
bhardwaj.ankit@nyu.edu
CV · Google Scholar · GitHub · LinkedIn
I am a PhD (Degree Pending) from Computer Science at the Courant Institute of Mathematical Sciences, New York University, advised by Lakshminarayanan Subramanian. My research is on artificial intelligence for decision making in societal-scale systems, where a regulator or an operator has to spend a limited public resource using measurements it cannot fully trust. I treat this as a loop of four steps, which are observability, attribution, intervention and response, and I work on it in air pollution, road traffic and public health. In each system I first ask how fine a distinction the available measurements can support, and then design the estimator, the attribution or the control law within that limit.
Before NYU, I received a B.Tech. in Computer Science and Engineering from IIT Kanpur in 2019 and spent two years as an Associate Machine Learning Scientist at Wadhwani AI, where I worked with India's national tuberculosis programme.
FieldFormer: Locality-Aware Transformers for Spatio-Temporal Modeling on Sparse Sensor Networks
Ankit Bhardwaj, Ananth Balashankar, Lakshminarayanan Subramanian
Transactions on Machine Learning Research, 2026. [Paper] [Code]
Self-Regulating Cars: Automating Traffic Control in Free Flow Road Networks
Ankit Bhardwaj, Rohail Asim, Sachin Kumar Chauhan, Yasir Zaki, Lakshminarayanan Subramanian
AAAI Conference on Artificial Intelligence (AAAI), AI for Social Impact track, 2026. Oral presentation. [Paper] [Code] [Video]
Comprehensive Monitoring of Air Pollution Hotspots Using Sparse Sensor Networks
Ankit Bhardwaj, Ananth Balashankar, Shiva Iyer, Nita Soans, Anant Sudarshan, Rohini Pande, Lakshminarayanan Subramanian
ACM Journal on Computing and Sustainable Societies, 2025. Presented at ACM COMPASS 2025. Selected for ACM Showcase. [Paper] [Code] [Slides] [ACM Showcase]
Predicting Treatment Adherence of Tuberculosis Patients at Scale
Mihir Kulkarni*, Satvik Golechha*, Rishi Raj Grandhe*, Jithin K. Sreedharan*, Ankit Bhardwaj, Santanu Rathod, Bhavin Vadera, Jayakrishna Kurada, Kirankumar Rade, Sanjay Mattoo, Rajendra Joshi, Alpan Raval
Machine Learning for Health Symposium (ML4H), 2022. Outstanding Paper Award. [Paper]
Oct 2026. Defended my PhD Thesis on "Mechanistic AI for Partially Observed Urban Systems: From Monitoring to Management".
Jul 2026. FieldFormer accepted at Transactions on Machine Learning Research.
Jul 2026. Joined Nash as an optimization research intern.
Apr 2026. “A Replication-Testing Framework for Single-Cell Gene Regulatory Edge Rankings” accepted for oral presentation at RECOMB-Genetics 2026.
Mar 2026. “Domain Faithfulness through Counterfactually Robust Learning” accepted at CLeaR 2026.
Jan 2026. Oral presentation of “Self-Regulating Cars” at AAAI 2026 in Singapore, supported by an AAAI student travel scholarship.
Oct 2025. Thesis proposal, “Mechanistic AI Systems for Complex Urban Processes”. The committee was Lerrel Pinto, Edwin Gerber, Anirudh Sivaraman and Lakshminarayanan Subramanian.