ECE Seminar with Sahand Neghaban
- 4:00 pm on Monday, March 25, 2013
- Photonics Center, 8 Saint Mary’s St., Room 339
Structured Estimation in High-Dimensions Sahand Neghaban Postdoctoral Associate Massachusetts Institute of Technology Faculty Host: Prakash Ishwar Refreshments will be served outside Room 339 at 3:45 p.m. Abstract: Modern techniques in data accumulation and sensing have led to an explosion in both the volume and variety of data. These advancements have presented us with a tremendous opportunity to perform more sophisticated inference and decision making tasks. Such problems arise in: genomics, rank aggregation, and recommendation systems. 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. The high-dimensionality and volume of the data leads to substantial challenges, both statistical and computational. A major focus of Dr. Neghaban’s work has been developing an understanding of how hidden low-complexity structure in large datasets can be used to develop computationally efficient estimation methods. He will introduce a unified framework for establishing the error behavior of a broad class of estimators under high-dimensional scaling. He will then discuss how to compute these estimates and draw connections between the statistical and computational properties of our methods. Interestingly, the same tools used to establish good high-dimensional estimation performance have a direct impact for optimization: better conditioned statistical problems lead to more efficient computational methods. [Joint work with Alekh Agarwal, Sewoong Oh, Pradeep Ravikumar, Devavrat Shah, Martin Wainwright and Bin Yu] About the Speaker: Sahand Negahban is currently a postdoctoral associate at MIT and advised by Devavrat Shah. He received a bachelor’s degree in electrical engineering and computer sciences (2006), master’s degree in statistics (2011), and Ph.D. in electrical engineering and computer sciences (2012), all from UC Berkeley. His research interests include machine learning, mathematical and high-dimensional statistics, convex optimization, and statistical signal processing. He was awarded a Vodafone Fellowship and a Yahoo! Key Scientific Challenges Award.