Jianhao Ma
 |
Jianhao Ma |
About me
I'm currently a third-year Ph.D. candidate at Umich. I am fortunate to be advised by Professor Salar Fattahi. My research focus on understanding the pratical success of gradient-based algorithms based on trajectory analysis. I welcome future collaborations. Please feel free to contact me via Email!
Research Interests
General optimization and generalization in modern machine learning.
Matrix factorization and tensor decomposition.
Empirical process and its application.
Preprints
On the Optimization Landscape of Burer-Monteiro Factorization: When do Global Solutions Correspond to Ground Truth? [arxiv]
Jianhao Ma, Salar Fattahi
Publications
Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization [arxiv]
Journal of Machine Learning Research (JMLR) 2023
Jianhao Ma, Salar Fattahi
Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition [arxiv]
International Conference on Learning Representations (ICLR) 2023
Jianhao Ma, Lingjun Guo, Salar Fattahi
Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution [arxiv]
Advances in Neural Information Processing Systems (NeurIPS) 2022 (Spotlight)
Jianhao Ma, Salar Fattahi
Towards Understanding Generalization via Decomposing Excess Risk Dynamics [paper] [arxiv]
International Conference on Learning Representations (ICLR) 2022
Jiaye Teng*, Jianhao Ma*, Yang Yuan
Sign-RIP: A Robust Restricted Isometry Property for Low-rank Matrix Recovery [paper][arxiv]
Jianhao Ma, Salar Fattahi
NeurIPS Workshop on Optimization for Machine Learning, 2021
News
February 2023: New paper about the global landscape of Burer-Monteiro factorization in low-rank matrix recovery problems.
February 2023: The paper Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization is accepted by Journal of Machine Learning Research.
January 2023: Our paper has been accepted in ICLR 2023.
October 2022: Receive the NeurIPS 2022 Scholar Award.
October 2022: New paper on the convergence of gradient descent: Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition. Joint work with Lingjun Guo and Salar Fattahi.
September 2022: Our paper Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution has been accepted in NeurIPS 2022! Joint work with my advisor Salar Fattahi.
June 2022: I will give a talk in INFORMS Annual Meeting, 2022.
Conference Services
Reviewer of ICML, NeurIPS, ICLR, AISTATS.
Quate
Always consider a problem under the minimum structure in which it makes sense. —— Gustave Choquet