Shahin Shahrampour
Assistant Professor, Mechanical and Industrial Engineering
Affiliated Faculty, Electrical and Computer Engineering
Office
- 269 SN
- 617.373.5750
Lab
- 009 FR
Related Links
Research Focus
Machine learning, optimization and control, distributed and sequential learning, with a focus on developing computationally efficient methods for data analytics
About
Shahin Shahrampour is currently an Assistant Professor in the Department of Mechanical & Industrial Engineering at Northeastern University. He was previously an Assistant Professor in the Departments of Industrial & Systems Engineering and Electrical & Computer Engineering (by courtesy) at Texas A&M University (TAMU) in 2018-2021. Before joining TAMU, he was a Postdoctoral Fellow in the School of Engineering and Applied Sciences at Harvard University. Prior to that, he received the Ph.D. degree in Electrical and Systems Engineering, the M.A. degree in Statistics (The Wharton School), and the M.S.E. degree in Electrical Engineering, all from the University of Pennsylvania, in 2015, 2014, and 2012, respectively.
Education
- PhD, Electrical & Systems Engineering, University of Pennsylvania – 2015
- AM, Statistics, The Wharton School – 2014
- MS, Electrical Engineering, University of Pennsylvania – 2012
- BS, Electrical Engineering, Sharif University of Technology – 2009
Research Overview
Machine learning, optimization and control, distributed and sequential learning, with a focus on developing computationally efficient methods for data analytics
Selected Research Projects
- Consensus and Distributed Optimization in Non-Convex Environments with Applications to Networked Machine Learning
- – Principal Investigator, National Science Foundation (NSF)
- Collaborative Online Optimization for Efficient Model-Based Learning
- – Principal Investigator, National Science Foundation (NSF)
- Real-Time Learning and Control of Stochastic Nanostructure Growth Processes Through in situ Dynamic Imaging
- – Co-Principal Investigator, National Science Foundation (NSF)
Department Research Areas
Selected Publications
- S. Chen, A. Garcia, and S. Shahrampour “On Distributed Non-convex Optimization: Projected Subgradient Method For Weakly Convex Problems in Networks”, IEEE Transactions on Automatic Control (TAC), Feb 2021
- S. Chen, A. Garcia, M. Hong, and S. Shahrampour “Decentralized Riemannian Gradient Descent on the Stiefel Manifold”, International Conference on Machine Learning (ICML), 2021
- L. Ding, R. Tuo, and S. Shahrampour “Generalization Guarantees for Sparse Kernel Approximation with Entropic Optimal Features”, International Conference on Machine Learning (ICML), 2020
- S. Shahrampour and A. Jadbabaie, “Distributed Online Optimization in Dynamic Environments Using Mirror Descent”, IEEE Transactions on Automatic Control (TAC), March 2018
- A. Beirami, M. Razaviayayn, S. Shahrampour, and V. Tarokh, “On Optimal Generalizability in Parametric Learning”, Advances in Neural Information Processing Systems (NeurIPS), 2017
Jun 12, 2023
Advancing Distributed Optimization for Non-Convex Problems
MIE Assistant Professor Shahin Shahrampour received a $500,000 NSF grant, in collaboration with Texas A&M University, to address “Consensus and Distributed Optimization in Non-Convex Environments with Applications to Networked Machine Learning.” The project will transform the understanding of consensus and coordination in non-convex environments, and will include educational components to introduce distributed optimization as a practical tool for the next generation of engineers.
Jul 12, 2022
Best Paper Award at IEEE ICASSP 2022
MIE Assistant Professor Shahin Shahrampour and his collaborators from Vanderbilt, INRIA, and Telecom Paris received the best paper award at the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) for their work on “Generalized Sliced Probability Metrics“.
Jul 09, 2021
New Faculty Spotlight: Shahin Shahrampour
Shahin Shahrampour joins the Mechanical and Industrial Engineering department in July 2021 as an Assistant Professor.