StochStatMIT: Sahand N. Negahban

Title: Structured Estimation in High-Dimensions Abstract: Modern techniques in data accumulation and sensing have led to an explosion in the complexity of data. Many of the resulting estimation problems are high-dimensional, meaning that the number of parameters to estimate can be far greater than the number of examples. A major focus of my work has been developing an understanding of how hidden low-complexity structure in large datasets can be used to develop computationally efficient estimation methods with strong statistical guarantees. I will discuss a variety of problems including collaborative rank aggregation from pairwise comparisons, low-rank matrix estimation, and robust parameter recovery. I will then discuss how to compute these estimates and draw connections between the statistical and computational properties of our methods. Bio: Sahand Negahban is currently an Assistant Professor in the Statistics Department at Yale University. Prior to that he has worked with Prof. Devavrat Shah at MIT as a Postdoc and Prof. Martin J. Wainwright at UC Berkeley as a Graduate student. The focus of his research is to develop theoretically sound methods, which are both computationally and statistically efficient, for extracting information from large datasets. A salient feature of his work has been to understand how hidden low-complexity structure in large datasets can be used to develop computationally and statistically efficient methods for extracting meaningful information for high-dimensional estimation problems. His work borrows from and improves upon tools of statistical signal processing, machine learning, probability and convex optimization.