Che-Ping Tsai

Che-Ping Tsai

Ph.D. student
at Carnegie Mellon University

Bio

I’m a fourth year PhD student in the Machine Learning Department at Carnegie Mellon University advised by Pradeep Ravikumar. I am generally interested in developing principled and practical algorithms in Artificial Intelligence (AI). My current focus involves delving into the mechanisms by which neural networks store knowledge and devising methods to extract this knowledge. The goal is to make AI systems more interpretable and reliable, so we can address alignment challenges.

Previously, I completed my M.S. degree in Computer Science & Information Engineering (CSIE) at National Taiwan University (NTU). I was a member of the Speech Processing Lab working with Lin-shan Lee and Prof. Hung-yi Lee. During my undergrad years, I pursued a dual major in Electrical Engineering and Mathematics at NTU.

Selected Publications

  • Sample based Explanations via Generalized Representers
    C.-P. Tsai, C.-K. Yeh, P. Ravikumar.
    In Advances in Neural Information Processing Systems (NeurIPS) 36, 2023.
    [paper]

  • Representer Point Selection for Explaining Regularized High-dimensional Models
    C.-P. Tsai, J. Zhang, H.-F. Yu, E. Chien, C.-J. Hsieh, P. Ravikumar.
    In International Conference on Machine Learning (ICML) 39, 2023
    [paper | code]

  • Faith-Shap: The Faithful Shapley Interaction Index
    C.-P. Tsai, C.-K. Yeh, P. Ravikumar.
    Journal of Machine Learning Research (JMLR), Vol. 24 (94), pages 1-42, 2023.
    [paper | code]

  • Heavy-tailed streaming statistical estimation
    C.-P. Tsai,A. Prasad, S. Balakrishnan, P. Ravikumar.
    In International Conference on Artificial Intelligence and Statistics (AISTATS) 25, 2022 (Oral).
    [paper]

Work experience

Services