About Me

I am a fifth-year Ph.D. student in the Department of Statistics at University of Washington advised by Zaid Harchaoui and Alex Luedtke. My research interests involve generative modeling, optimal transport & gradient flows, causal inference, and machine learning in general. At UW, I am fortunate to be working with Soumik Pal on optimal transport. I also work in collaboration with the Abrahms’s Lab and eScience Institute on developing AI tools for ecology.

I did my undergraduate in Mathematics from Indian Institute of Technology Kanpur with a minor in English literature. At IITK, I worked on developing methods for output analysis and convergence diagnostics of Markov chain Monte Carlo and importance sampling with Dootika Vats.

Contact me at medhaaga [at] uw [dot] edu.

News

Winter 2026 Looking forward to be a Visiting Scholar at the Harvard Medical School.

July 2025 Our paper titled Leveraging machine learning and accelerometry to classify animal behaviours with uncertainty is published at the Journal of Methods in Ecology and Evolution.

June 2025 Looking forward to attend the workshop on Wasserstein Gradient Flows in Math and Machine Learning at Banff International Research Station.

Feb 2025 Gave a talk at the IFML Mathematics of Deep Learning Workshop in Austin, TX. [Slides]

Feb 2025 Gave a talk at the UW Data Science Seminar titled Revealing the Hidden Lives of Cryptic Carnivores with Machine Learning and AI. Check out the YouTube video! [Slides]

Jan 2025 Gave a talk titled Pre-trained Transformer Learning as Heat Flows at the JMM 2025 AMS Special Session on MRC Mathematics of Adversarial, Interpretable, and Explainable AI. [Slides]

Selected Publications

Leveraging machine learning and accelerometry to classify animal behaviours with uncertainty
Medha Agarwal, Kasim Rafiq, Ronak Mehta, Briana Abrahms, Zaid Harchaoui
Accepted at Methods in Ecology and Evolution (2025)

[Paper] [Project Page] [Code] [Dataset]