Kimia Nadjahi

Kimia Nadjahi is a School of Engineering Distinguished Postdoctoral Fellow whose research bridges the fields of machine learning (ML) and computational optimal transport. Her current work is focused on the sliced Wasserstein distance (SW), a relatively recent idea in the theory and practice of optimal transport. As a doctoral candidate, Kimia designed ML algorithms balancing practical advantages and theoretical justification, with the aims of enhancing their efficiency and scalability, expanding theoretical grounding, and improving robustness to missing data. In her postdoctoral research, Kimia plans to develop a theoretically grounded, scalable methodology to make predictions from high-dimensional, temporal data with missing entries, a crucial capability for applications in medicine and many other domains. She also hopes to pursue interdisciplinary collaborations to establish whether a connection can be established between SW for non-Euclidean data and generalized SW; establishing a metric for non-Euclidian data could have a powerful impact on numerous fields, including bioinformatics, neurology, life sciences and text mining.