Lai TIAN
 |
|
About me
I am currently a final-year graduate student at CUHK, where I am very fortunate to be advised by Prof. Anthony Man-Cho So. Prior to this, I obtained my B.E. and M.E. degrees from Northwestern Polytechnical University.
Research interests
My main research interests are generally in mathematical optimization theory and its applications in modern machine learning. Recently, I am especially interested in nonsmooth analysis, metric regularity theory, and approximation algorithms.
What's new?
[Oct, 2024] One paper is accepted by SODA 2025.
[Oct, 2023] One paper is accepted for publication in Mathematical Programming.
[Oct, 2023] I attended the 2023 INFORMS Annual Meeting in Phoenix.
[May, 2022] One paper is accepted by ICML 2022.
Selected works [Google Scholar]
Testing Approximate Stationarity Concepts for Piecewise Affine Functions
Lai Tian, Anthony Man-Cho So
ACM-SIAM Symposium on Discrete Algorithms (SODA), 2025.
No Dimension-Free Deterministic Algorithm Computes Approximate Stationarities of Lipschitzians
Lai Tian, Anthony Man-Cho So
Mathematical Programming, Series A, 2024. [paper]
On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions
Lai Tian, Kaiwen Zhou, Anthony Man-Cho So
International Conference on Machine Learning (ICML), 2022. [paper]
Computing D-Stationary Points of \(\rho\)-Margin Loss SVM
Lai Tian, Anthony Man-Cho So
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022. [paper], [code]
Learning Feature Sparse Principal Subspace
Lai Tian, Feiping Nie, Rong Wang, Xuelong Li
Advances in Neural Information Processing Systems (NeurIPS), 2020. [paper], [code]