Preprints:
- A Parametric Approach for Solving Quadratic Optimization with Indicators Over Trees, submitted, 2024
A. Bhathena, S. Fattahi, A. Gomez, and S. Küçükyavuz - Can Learning Be Explained By Local Optimality In Low-rank Matrix Recovery?, submitted, 2024,
J. Ma and S. Fattahi
– INFORMS Junior Faculty Interest Group (JFIG) Best Paper Award – Second Place, 2023. - Solution Path of Time-varying Markov Random Fields with Discrete Regularization, submitted, 2023,
S. Fattahi and A. Gomez - Heterogeneous Matrix Factorization: When Features Differ by Datasets, submitted, 2023,
N. Shi, R. Al Kontar, and S. Fattahi
– INFORMS Data Mining Best Student Paper Award – Finalist, 2023. - Simple Alternating Minimization Provably Solves Complete Dictionary Learning, submitted, 2022,
G. Liang, G. Zhang, S. Fattahi, and R. Y. Zhang
Journal Papers:
- Triple Component Matrix Factorization: Untangling Global, Local, and Noisy Components, Journal of Machine Learning Research, 2024,
N. Shi, S. Fattahi, R. Al Kontar - Efficient Inference of Spatially-varying Gaussian Markov Random Fields with Applications in Gene Regulatory Networks, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2023,
V. Ravikumar, T. Xu, W. N. Al-Holou, S. Fattahi, and A. Rao - Preconditioned Gradient Descent for Overparameterized Nonconvex Burer–Monteiro Factorization with Global Optimality Certification, Journal of Machine Learning Research, 2023,
G. Zhang, S. Fattahi, and R. Y. Zhang - Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization, Journal of Machine Learning Research, 2023,
J. Ma and S. Fattahi - A Graph-based Decomposition Method for Convex Quadratic Optimization with Indicators, Mathematical Programming, 2022,
P. Liu, S. Fattahi, A. Gomez, and S. Küçükyavuz - Absence of Spurious Local Trajectories in Time-varying Optimization, to appear in IEEE Transactions on Automatic Control, 2021,
S. Fattahi, C. Josz, R. Mohammadi, J. Lavaei, and S. Sojoudi - Sample Complexity of Sparse System Identification, IEEE Transactions on Control of Network Systems, 2021,
S. Fattahi and S. Sojoudi - Smoothing Property of Load Variation Promotes Finding Global Solutions of Time-Varying Optimal Power Flow, IEEE Transactions on Control of Network Systems, 2021,
J. Mulvaney-Kemp, S. Fattahi, and J. Lavaei - Efficient Learning of Distributed Linear-Quadratic Controllers, SIAM Journal on Control and Optimization, 2020,
S. Fattahi, N. Matni, and S. Sojoudi - Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis, Journal of Machine Learning Research, 2020,
S. Fattahi and S. Sojoudi - Graphical Lasso and Thresholding: Equivalence and Closed-form Solutions, Journal of Machine Learning Research, 2019,
S. Fattahi and S. Sojoudi
INFORMS Data Mining Best Paper Award, 2018.
Katta G. Murty Best Paper Award, 2018. - Convexification of Generalized Network Flow Problem, Mathematical Programming, 2019,
S. Sojoudi, S. Fattahi and J. Lavaei - A Bound Strengthening Method for Optimal Transmission Switching in Power Systems, to appear in IEEE Transactions on Power Systems, 2019,
S. Fattahi, J. Lavaei and A. Atamturk - Linear-Time Algorithm for Learning Large-Scale Sparse Graphical Models, IEEE Access, 2019,
S. Fattahi and S. Sojoudi - Transformation of Optimal Centralized Controllers Into Near-Global Static Distributed Controllers, IEEE Transactions on Automatic Control, 2019,
S. Fattahi, G. Fazelnia and J. Lavaei - Conic Relaxation of the Unit Commitment Problem, Energy, 2017,
S. Fattahi, M. Ashraphijou, J. Lavaei and A. Atamturk
Conference Papers:
- Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion, Conference on Learning Theory, 2024
J. Ma and S. Fattahi - Robust Sparse Mean Estimation via Incremental Learning, International Conference on Learning Representations, BGPT Workshop: Bridging the Gap Between Practice and Theory in Deep Learning, 2024,
J. Ma, R. Ren Chen, Y. He, S. Fattahi, and W. Hu - Personalized Dictionary Learning for Heterogeneous Datasets, Neural Information Processing Systems, 2023,
G. Liang, N. Shi, R. Al Kontar, and S. Fattahi - Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition, International Conference on Learning Representations, 2023,
J. Ma, L. Guo, and S. Fattahi - Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution, Neural Information Processing Systems, Spotlight (top 3%), 2022,
J. Ma and S. Fattahi - Sign-RIP: A Robust Restricted Isometry Property for Low-rank Matrix Recovery, Neural Information Processing Systems, Workshop on Optimization for Machine Learning, 2021,
J. Ma and S. Fattahi - Preconditioned Gradient Descent for Over-parameterized Nonconvex Matrix Factorization, Neural Information Processing Systems, 2021,
G. Zhang, S. Fattahi, R.Y. Zhang - Scalable Inference of Sparsely-changing Gaussian Markov Random Fields, Neural Information Processing Systems, 2021,
S. Fattahi and A. Gomez - Learning Partially Observed Linear Dynamical Systems from Logarithmic Number of Samples, Learning for Dynamics & Control Conference, 2021,
S. Fattahi - Load Variation Enables Escaping Poor Solutions of Time-Varying Optimal Power Flow, IEEE Power & Energy Society General Meeting, 2020,
J. Mulvaney-Kemp, S. Fattahi, and J. Lavaei
– Best Conference Paper Award (one of multiple awards) - Learning Sparse Dynamical Systems from a Single Sample Trajectory, IEEE Conference on Decision and Control, 2019,
S. Fattahi, N. Matni, and S. Sojoudi - Data-Driven Sparse System Identification, 56th Annual Allerton Conference on Communication, Control, and Computing, 2018
S. Fattahi and S. Sojoudi - Non-Asymptotic Analysis of Block-Regularized Regression Problem, IEEE Conference on Decision and Control, 2018
S. Fattahi and S. Sojoudi - Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion, International Conference on Machine Learning, 2018
R. Y. Zhang, S. Fattahi and S. Sojoudi - Sparse Inverse Covariance Estimation for Chordal Structures, European Control Conference, 2018
S. Fattahi, R. Y. Zhang and S. Sojoudi - Closed-Form Solution and Sparsity Path for Inverse Covariance Estimation Problem, American Control Conference, 2018
S. Fattahi and S. Sojoudi
– Best Paper Award-Finalist. - High-Performance Cooperative Distributed Model Predictive Control for Linear Systems, American Control Conference, 2018
G. Darivianakis, S. Fattahi, J. Lygeros and J. Lavaei - Promises of Conic Relaxations in Optimal Transmission Switching of Power Systems, IEEE Conference on Decision and Control,2017
S. Fattahi, J. Lavaei and A. Atamturk - A Scalable Method for Designing Distributed Controllers for Systems with Unknown Initial States, IEEE Conference on Decision and Control, 2017
S. Fattahi, J. Lavaei and M. Arcak - On the Convexity of Optimal Decentralized Control Problem and Sparsity Path, American Control Conference, 2017
S. Fattahi and J. Lavaei - Theoretical Guarantees for the Design of Near Globally Optimal Static, 54th Annual Allerton Conference on Communication, Control, and Computing, 2016
S. Fattahi and J. Lavaei - A Strong Semidefinite Programming Relaxation of the Unit Commitment Problem, IEEE Conference on Decision and Control, 2016
M. Ashraphijou, S. Fattahi, J. Lavaei and A. Atamturk - Convex Analysis of Generalized Flow Networks, IEEE Conference on Decision and Control, 2015
S. Fattahi and J. Lavaei - Transformation of Optimal Centralized Controllers Into Near-Global Static Distributed Controllers, IEEE Conference on Decision and Control, 2015
S. Fattahi, G. Fazelnia and J. Lavaei - An Algorithm for Detecting Exact Regions of Moving Objects in Video Frames, International Symposium on Telecommunication, 2014
S. Fattahi, M. Azghani and F. Marvasti