Representative Publications

  1. Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion, submitted, 2024
          J. Ma and S. Fattahi
  2. 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) Paper Competition (Second Place) 2023. 
  3. Solution Path of Time-varying Markov Random Fields with Discrete Regularization, submitted, 2023,
          S. Fattahi and A. Gomez
  4. Personalized Dictionary Learning for Heterogeneous Datasets, NeurIPS 2023,
          G. Liang, N. Shi, R. Al Kontar, and S. Fattahi
  5. 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
  6. 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
  7. 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
  8. Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition, ICLR 2023,
          Jianhao Ma, Lingjun Guo, and Salar Fattahi
  9. Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution, NeurIPS 2022, Spotlight (top 3%),
          Jianhao Ma and Salar Fattahi
  10. A Graph-based Decomposition Method for Convex Quadratic Optimization with Indicators, Mathematical Programming, 2022,
           P. Liu, S. Fattahi, A. Gomez, and S. Küçükyavuz
           – INFORMS Computing Society Best Student Paper Award (Runner Up), 2022.
  11. Preconditioned Gradient Descent for Over-parameterized Nonconvex Matrix Factorization, NeurIPS 2021,
           G. Zhang, S. Fattahi, R.Y. Zhang
  12. Scalable Inference of Sparsely-changing Gaussian Markov Random FieldsNeurIPS 2021,
           S. Fattahi and A. Gomez
  13. 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
  14. 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.
  15. Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion, ICML 2018,
           R. Y. Zhang, S. Fattahi and S. Sojoudi