Publications include 'On the Hardness of Conditional Independence Testing In Practice' (NeurIPS 2025), 'Efficient Conditionally Invariant Representation Learning' (ICLR 2023, Top 5% Oral Presentation), 'MMD-B-Fair: Learning Fair Representations with Statistical Testing' (AISTATS 2023), and 'Learning Privacy-Preserving Deep Kernels with Known Demographics' (PPAI-22 2022).
Research Experience
Held machine learning research intern positions at Borealis AI, the Visual Intelligence and Learning Lab at EPFL, and the Applied Sciences group at Microsoft Research India. Also has full-time experience as a research fellow at Wadhwani AI.
Education
Ph.D. in Machine Learning, ongoing, Carnegie Mellon University, advised by Dr. Kun Zhang and Dr. Jeff Schneider; MSc. in Computer Science, 2023, The University of British Columbia, advised by Dr. Danica J. Sutherland; BTech. (Honors) in Computer Science & Engineering, 2017, Indraprastha Institute of Information Technology.
Background
Interests: Artificial Intelligence, Causal Learning, Computer Vision, Reinforcement Learning, Wildlife Conservation. Current research focus is on developing theory and algorithms to learn causal representations for reinforcement learning, generative modelling, video understanding, and robustness in deep learning.