Sara Fridovich-Keil

Sara Fridovich-Keil is an Assistant Professor in the School of Electrical and Computer Engineering at Georgia Tech, where she is also program faculty in machine learning. Previously, she was a postdoctoral researcher at Stanford University (2023–2025), advised by Gordon Wetzstein and Mert Pilanci, and completed her Ph.D. in Electrical Engineering and Computer Sciences at UC Berkeley in 2023 under the guidance of Ben Recht. Her research focuses on the foundations of machine learning, signal processing, and optimization, with applications to computational imaging, medical imaging (e.g., MRI, CT, cryo-EM), and inverse problems.

Her work bridges theory and practice, addressing challenges such as nonlinear tomographic reconstruction, data-driven prior design, and signal representation for inverse problems. Key contributions include Plenoxels (radiance field reconstruction without neural networks) and K-Planes (space-time appearance modeling). She is supported by an NSF Mathematical Sciences Postdoctoral Research Fellowship and has received the UC Berkeley Demetri Angelakos Memorial Achievement Award (2022).

Her lab at Georgia Tech seeks to develop scalable, provably accurate algorithms for imaging applications. She advises students interested in machine learning, optimization, and signal processing. Professional activities include membership on the IEEE Signal Processing Society’s Computational Imaging Technical Committee (2025–2027).

Personal interests include hiking, gardening, and open-source contributions (e.g., GitHub repositories like Plenoxels and FingertipVideo for vital sign estimation).