Location
2753 IOE
Phone
Primary Website
Biography
Personal Pronouns
he/him
Prof. Fattahi is an assistant professor of Industrial and Operations Engineering at the University of Michigan. He has been the recipient of a National Science Foundation CAREER Award and the Deans’ MLK Spirit Award. His research has been recognized by multiple awards, including multiple best paper awards from INFORMS. He serves as an Associate Editor for the INFORMS Journal on Data Science, and as an area chair for several premier conferences, including NeurIPS, ICML, and ICLR. His research has been supported by multiple grants, including two from the National Science Foundation and one from the Office of Naval Research.
Education
- PhD, University of California, Berkeley, 2020, Industrial Engineering and Operations Research
- MS, Columbia University, 2015, Electrical Engineering
- BS, Sharif University of Technology, 2014, Electrical Engineering
Research Interests
Prof. Fattahi’s research focuses on developing efficient and scalable computational methods for structured problems. In particular, he exploits inherent structures in optimization and machine learning problems, such as sparsity, low-rankness, and benign landscape, to develop computational techniques that scale gracefully and enjoy strong guarantees.
- Machine Learning
Professional Society Memberships
Awards
Sample Publications
- P. Liu, S. Fattahi, A. Gomez, and S. Küçükyavuz, “A Graph-based Decomposition Method for Convex Quadratic Optimization with Indicators”, Mathematical Programming, 2022
- S. Fattahi and A. Gomez, “Scalable Inference of Sparsely-changing Gaussian Markov Random Fields”, Conference on Neural Information Processing Systems (NeurIPS), 2021
- S. Fattahi, Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples, Learning for Dynamics & Control Conference, 2021
- G. Zhang, S. Fattahi, R.Y. Zhang, “Preconditioned Gradient Descent for Over-parameterized Nonconvex Matrix Factorization”, Conference on Neural Information Processing Systems (NeurIPS), 2021,
- S. Fattahi and S. Sojoudi, “Exact Guarantees on the Absence of Spurious Local Minima for Rank-1 Non-negative Robust Principal Component Analysis”, Journal of Machine Learning Research, 2020.
- S. Fattahi, N. Matni, and S. Sojoudi, “Efficient Learning of Distributed Linear-Quadratic Regulators”, SIAM Journal on Control and Optimization, 2020
- S. Fattahi and S. Sojoudi, “Graphical Lasso and Thresholding: Equivalence and Closed-Form Solutions”, Journal of Machine Learning Research, 2020.
- S. Sojoudi, S. Fattahi and J. Lavaei, “Convexification of Generalized Network Flow Problem”, Mathematical Programming, 2019.