I am a postdoctoral researcher working with Eero Simoncelli at the Flatiron Institute. My research lies at the intersection of computer vision, machine learning, and information theory. Particularly, my goal is to bridge the gap between human and computational vision by (1) formulating the mathematical principles that underlie human perception (e.g., establishing an unsupervised learning theory for image perceptual quality metrics), and by (2) using these principles to develop optimal algorithms and evaluation criteria for core computer vision applications, such as image restoration and compression. In the long term, I believe that such principles and algorithms could also play a significant role in elucidating the mechanisms of biological sensory systems.

Previously, I received a PhD in Computer Science from the Technion—Israel Institute of Technology, where I was advised by Michael Elad and Tomer Michaeli. My doctoral research focused on designing image restoration and compression algorithms that are based on generative models, as well as understanding their theoretical limitations. You can download my PhD dissertation from this link.