About me
Hi, I am Yongchan Kwon, an Assistant Professor in the Department of Statistics at Columbia University. My research focuses on developing more interpretable and rigorous machine learning methods, directly motivated by scientific questions. I received a Ph.D. at Seoul National University (Advisor: Prof. Myunghee Cho Paik) and did postdoc at Stanford University (Mentor: Prof. James Zou).
Experience
- Assistant Professor, Department of Statistics, Columbia University, 2022 - Current
- Postdoc Researcher, Department of Biomedical Data Science, Stanford University, 2020 - 2022
Education
- Ph.D in Statistics, Seoul National University, 2013 - 2020
- B.S. in Mathematical Sciences, Korea Advanced Institute of Science and Technology (KAIST), 2009 - 2013
Selected Publications
Sun, Y., Shen, J., and Kwon, Y. (2024). 2D-OOB: Attributing Data Contribution through Joint Valuation Framework. Advances in Neural Information Processing Systems (NeurIPS 2024). [URL]. [GitHub].
Wang, J.T., Yang, T., Zou, J., Kwon, Y., and Jia, R. (2024). Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits. International Conference on Machine Learning (ICML 2024). (selected for oral presentation, Top 1.5%). [URL].
Kwon, Y.*, Wu, E.*, Wu, K.*, and Zou, J. (2024). DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models. International Conference on Learning Representations. (ICLR 2024). [URL]. [GitHub].
Jiang, K.*, Liang, W.*, Zou, J. and Kwon, Y.* (2023). OpenDataVal: a Unified Benchmark for Data Valuation. Advances in Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks. [URL]. [Website]. [GitHub].
Kwon, Y. and Zou, J. (2023). Data-OOB: Out-of-bag Estimate as a Simple and Efficient Data Value. International Conference on Machine Learning (ICML 2023). [URL]. [GitHub].
Kwon, Y. and Zou, J.. (2022). Beta-Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning. Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022), PMLR 151:8780-8802. [URL]. [GitHub]. (selected for oral presentation, Top 2.6%).
Contact
Email: yk3012 (at) columbia (dot) edu