Rocco Servedio is an associate professor of computer science at Columbia Engineering. His research focuses on computational learning theory and computational complexity. He is particularly interested in foundational questions of understanding what types of learning problems have—and do not have—computationally efficient algorithms. A major goal of his research is the design and analysis of computationally efficient algorithms for challenging learning problems involving noisy data and complex target functions. A related interest is the study of “low-level” computational models such as decision trees, shallow circuits, and low-degree polynomials. Servedio was an NSF Mathematical Sciences postdoc at Harvard before joining Columbia. He has received an NSF Career Award and a Sloan Foundation Fellowship, and his research is supported by DARPA, Google, and the National Science Foundation. Servedio received his A.B. in mathematics and Ph.D.in computer science from Harvard.