Tselil received her PhD in Computer Science from UC Berkeley, and completed postdoctoral work at Harvard and MIT. She has completed research fellowships for both Microsoft and Google while at the Simons Institute for the Theory of Computing. Also in 2020, she was a visiting researcher at the Weizmann Institute of Science and with the Machine Learning and Optimization Group at Microsoft Research.
I am broadly interested in the theory of algorithms, optimization, and computational complexity for problems arising in statistics. My work aims to develop algorithmic tools for high-dimensional estimation problems and to characterize and explain information/computation tradeoffs. Some specific themes in my research are: understanding the algorithmic power of the sum-of-squares hierarchy of semidefinite programs; developing fast spectral methods; and relating the power of different models of computation for high-dimensional estimation tasks.