KIM, Jakwang

Assistant Professor

Education Background

Ph.D. in Statistics(minor Mathematics), University of Wisconsin, Madison (2017-2023, advised by Nicolas Garcia Trillos)

Academic Area
Artificial Intelligence, Computer Science, Machine Learning and Artificial Intelligence, Operations Research, Optimization, Applied Probabilities and Stochastic System, Financial Engineering, Statistics, Statistical Theory, Financial Statistics
Research Field
Optimal Transport, Spin Glass, Learning Theory, Theory of Deep Learning, Statistical Inference of High Dimensional Discrete Problems
Personal Website
Email
jakwangkim@cuhk.edu.cn
Office
Room 404c, Zhi Xin Building
Biography

Jakwang Kim is an assistant professor of School of Data Science, Chinese University of Hong Kong, Shenzhen. Prior to this, he was a postdoctoral researcher in the PIMS Kantotrovich Initiative Postdoctoral Fellow at the University of British Columbia, Vancouver jointly advised by Prof. Young-Heon Kim, Prof. Soumik Pal(UW-Seattle), Prof. Khanh Dao Duc, and Prof. Geoffrey Schiebinger. He received his Ph.D. in Statistics from the University of Wisconsin-Madison in 2023 advised by Prof. Nicolas Garcia Trillos. Before Ph.D, he received B.A and M.A in Economics from Korea University in Korea.

Academic Publications

1. The multimarginal optimal transport formulation of adversarial multiclass classification (joint work with Nicolas Garcia Trillos and Matt Jacobs)
Journal of Machine Learning Research

2. On the existence of solutions to adversarial training in multiclass classification (joint work with Nicolas Garcia Trillos and Matt Jacobs)
European Journal of Applied Mathematics

3. An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification (joint work with Nicolas Garcia Trillos, Matt Jacobs and Matt Werenski)
Journal of Machine Learning Research

4. Optimal sequencing depth for single-cell RNA-sequencing in Wasserstein space (joint work with Geoffrey Schiebinger, Sharvaj Kubal)
Annals of Statistics(to appear)