Skip to main content

Ehsan Elhamifar

Assistant Professor

Affiliate Faculty with the Department of Electrical and Computer Engineering

Contact

Office Location

440 Huntington Avenue
310E West Village H
Boston, MA 02115

Mailing Address

Northeastern University
ATTN: Ehsan Elhamifar, 202 WVH
360 Huntington Avenue
Boston, MA 02115

Research Interests

  • Machine learning, with a focus in subset selection, zero and few shot learning, manifold clustering, high-rank matrix completion, nonlinear dynamical models, and deep neural networks
  • Computer vision, with a focus in procedure learning, video summarization, large-scale multi-label recognition, motion and activity segmentation, and active learning for visual data
  • Optimization, with a focus in sparse and low-rank recovery, structured submodular maximization, and convex and non-convex optimization

Education

  • PhD in Electrical and Computer Engineering, Johns Hopkins University
  • MS in Applied Mathematics and Statistics, Johns Hopkins University
  • MS in Electrical Engineering, Sharif University of Technology, Iran

Biography

Ehsan Elhamifar is an assistant professor in the Khoury College of Computer Sciences and director of the Mathematical, Computational and Applied Data Science Lab at Northeastern University. He is affiliated with Northeastern’s electrical and computer engineering department. Elhamifar is a recipient of the DARPA Young Faculty Award and the NSF CISE Career Research Initiation Initiative Award. Previously, he was a postdoctoral scholar in the electrical engineering and computer science department at University of California, Berkeley.

Elhamifar’s research areas are machine learning, computer vision, and optimization. He is interested in developing scalable, robust, and provable algorithms to address challenges of complex and massive high-dimensional data. He applies these tools in areas such as computer vision and robotics. Specifically, he uses tools from convex, non-convex, and submodular optimization; sparse and low-rank modeling; deep learning; high-dimensional statistics; and graphical models to develop algorithms and theory. He applies these discoveries to real-world challenges, including big data summarization, procedure learning from instructional data, large-scale recognition with small labeled data, and active learning for visual data.