Shirin Shoushtari

I am a Ph.D. candidate in Electrical and Systems Engineering at Washington University in St. Louis, advised by Prof. Ulugbek S. Kamilov in the Computational Imaging Group.

I develop theory and algorithms for deep learning-based imaging inverse problems, with an emphasis on optimization-driven methods, generative models, and robustness under distribution shift. My work spans convergence analysis of plug-and-play and diffusion-based solvers, out-of-distribution detection, and measuring distribution shift directly from measurements, with applications to computational and quantitative MRI.

Going forward, I am particularly interested in flow matching: its deep connections to optimization and minimization theory, and how those connections can be used to design principled solvers for imaging inverse problems with provable guarantees. You can read more on my research page.

Before WashU, I received my M.Sc. and B.Sc. in Electrical Engineering from Sharif University of Technology. Outside of research, I enjoy literature and philosophy, classical music, film, and learning languages.