Sara Fridovich-Keil is an assistant professor in the School of Electrical and Computer Engineering, and program faculty in machine learning. Before joining Georgia Tech, Fridovich-Keil was a postdoc at Stanford and completed her Ph.D. at UC Berkeley in 2023 and her B.S.E. at Princeton in 2018. Her research focuses on foundations and applications of machine learning and signal processing in computational imaging.
- Ph.D., Electrical Engineering and Computer Sciences, University of California, Berkeley, 2023
- B.S.E., Electrical Engineering, Princeton University, 2018
Fridovich-Keil’s research involves machine learning, signal processing, and optimization for solving inverse problems in computational imaging, including computer vision as well as medical and scientific imaging. Her research spans foundational theoretical questions and practical algorithm and method development for imaging applications.
Fridovich-Keil’s teaching interests include foundational and advanced courses in electrical and computer engineering with an emphasis on signal and image processing and computational imaging. Her teaching approach fosters a deep understanding of theoretical principles alongside practical applications, encouraging student participation and collaboration.
- NSF Mathematical Sciences Postdoctoral Research Fellowship, 2023
- IEEE Signal Processing Society Computational Imaging Technical Committee Member, 2025-2027
- UC Berkeley Demetri Angelakos Memorial Achievement Award, 2022
- M Lou, KA Verchand, S Fridovich-Keil, and A Pananjady, “Accurate, provable, and fast nonlinear tomographic reconstruction: A variational inequality approach,” SIAM Imaging Sciences (to appear), 2026.
- · N Kim and S Fridovich-Keil, “Grids Often Outperform Implicit Neural Representations at Compressing Dense Signals,” NeurIPS, 2025.
- · S Fridovich-Keil and M Pilanci, “A Recovery Guarantee for Sparse Neural Networks,” ICLR, 2026.
- · I Sivgin, S Fridovich-Keil, G Wetzstein, and M Pilanci, “Geometric Algebra Planes: Convex Implicit Neural Volumes,” ICML, 2025.
- · R Sanda, A Aali, A Johnston, EP Reis, G Wetzstein, and S Fridovich-Keil, “PaDIS-MRI: Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstruction,” ML4H, 2025.