Tselil Schramm

Tselil Schramm is an Assistant Professor at Stanford University, with courtesy appointments in the Department of Computer Science and Department of Mathematics. Her research bridges Theoretical Computer Science and Statistics, focusing on algorithmic tools for high-dimensional estimation and information-computation tradeoffs.

• PhD: UC Berkeley (advised by Prasad Raghavendra and Satish Rao)
• Postdoc: Harvard and MIT (hosted by Boaz Barak, Jon Kelner, Ankur Moitra, Pablo Parrilo)

Her work spans algorithms, optimization, and computational complexity in statistical contexts. Recent articles explore semidefinite programming, approximate message passing, and random geometric graphs, reflecting her focus on bridging discrete and continuous optimization for statistical inference.

Scientific Awards:

• NSF CAREER award
• Stanford Gabilan Fellowship
• Microsoft Research Fellow
• Google Research Fellow

Teaching: She has taught courses like Machine Learning Theory, Probability Theory, and The Sum-of-Squares Algorithmic Paradigm in Statistics at Stanford since 2021.