| Global convergence of sub-gradient method for robust matrix recovery: Small initialization, noisy measurements, and over-parameterization J Ma, S Fattahi Journal of Machine Learning Research, 2022 | 23 | 2022 |
| Sign-RIP: A robust restricted isometry property for low-rank matrix recovery J Ma, S Fattahi 2021 NeurIPS Workshop on Optimization for Machine Learning, 2021 | 18* | 2021 |
| Blessing of Depth in Linear Regression: Deeper Models Have Flatter Landscape Around the True Solution J Ma, S Fattahi Advances in Neural Information Processing Systems, 2022 | 11* | 2022 |
| Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition J Ma, L Guo, S Fattahi ICLR 2023, 2022 | 8 | 2022 |
| Towards Understanding Generalization via Decomposing Excess Risk Dynamics J Teng, J Ma, Y Yuan ICLR 2022, 2021 | 3 | 2021 |
| Can Learning Be Explained By Local Optimality In Low-rank Matrix Recovery? J Ma, S Fattahi arXiv preprint arXiv:2302.10963, 2023 | 1 | 2023 |
| On the Optimization Landscape of Burer-Monteiro Factorization: When do Global Solutions Correspond to Ground Truth? J Ma, S Fattahi arXiv preprint arXiv:2302.10963, 2023 | 1 | 2023 |
| Convergence of Gradient Descent with Small Initialization for Unregularized Matrix Completion J Ma, S Fattahi arXiv preprint arXiv:2402.06756, 2024 | | 2024 |
| Robust Sparse Mean Estimation via Incremental Learning J Ma, RR Chen, Y He, S Fattahi, W Hu arXiv preprint arXiv:2305.15276, 2023 | | 2023 |
Salar FattahiAssistant Professor, University of MichiganVerified email at umich.edu
