Biography
I am a final year PhD student in Applied Mathematics at Cornell University, where I am fortunate to be advised by Ziv Goldfeld. My research interests include mathematical theories for machine learning and high dimensional statistics, with a particular focus on optimal transport. My recent focus centers on the Gromov-Wasserstein distance, which is a fascinating interplay between classial optimal transport and metric geometry.
Interests
- Optimal Transport
- Statistical learning theory
- Artificial Intelligence
Education
PhD in Applied Mathematics, 2019-
Cornell University
BS in Mathematics and Applied Mathematics, 2015-2019
Shanghai Jiao Tong University
Experience
Publications
(2024).
Gradient Flows and Riemannian Structure in the Gromov-Wasserstein Geometry.
arXiv preprint arXiv:2407.11800.
(2024).
Gromov-Wasserstein Distances: Entropic Regularization, Duality, and Sample Complexity.
Accepted to the Annals of Statistics.
(2022).
Cycle consistent probability divergences across different spaces.
International Conference on Artificial Intelligence and Statistics.
(2021).
Non-asymptotic performance guarantees for neural estimation of f-divergences.
International Conference on Artificial Intelligence and Statistics.
Teaching
TA for:
* Fall 2020: ECE 4110 Random Signals in Communications and Signal Processing
* Fall 2021: ECE 4110 COMBINED-XLIST Random Signals in Communications and Signal Processing
* Spring 2022: MATH 4710 Basic Probability
* Fall 2022: MATH 4220/5220 Applied Complex Analysis
* Spring 2023: MATH 4140 Honors Introduction to Analysis II
* Spring 2024: ECE 4200 Fundamentals of Machine Learning