Che-Ping Tsai

Che-Ping Tsai

Ph.D. student
at Carnegie Mellon University

Bio

I’m a final-year PhD student in the Machine Learning Department at Carnegie Mellon University, advised by Pradeep Ravikumar. My research centers around statistical machine learning, with a focus on developing principal algorithms for representation learning and interpretability. I interned at Amazon as an applied scientist, where I worked on large language models for tabular data and recommender systems.

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, working on speech recognition and multi-label classification. During my undergrad years, I pursued a dual major in Electrical Engineering and Mathematics at NTU. I used to compete in mathematics and programming contests, earning two silver medals at the IMO and placing among the top 30 participants in the national IOI training camp.

I’m on the industry job market, seeking research scientist positions starting Jan/Feb 2026! Feel free to email me if there’s a fit! Here’s my CV.

Publications

  • Contextures: Representations from Contexts
    Runtian Zhai, Kai Yang, Che-Ping Tsai*, Burak Varici, Zico Kolter, Pradeep Ravikumar
    *In International Conference on Machine Learning (ICML), 2025
    [paper]

  • AnoLLM: Large Language Models for Tabular Anomaly Detection
    Che-Ping Tsai, Phil Wallis, Ganyu Teng, Wei Ding.
    In International Conference on Learning Representations (ICLR), 2025.
    [paper | code]

  • Sample based Explanations via Generalized Representers
    Che-Ping Tsai, Chih-Kuan Yeh, Pradeep Ravikumar.
    In Advances in Neural Information Processing Systems (NeurIPS), 2023.
    [paper]

  • Representer Point Selection for Explaining Regularized High-dimensional Models
    Che-Ping Tsai, Jiong Zhang, Hsiang-Fu Yu, Eli Chien, Cho-Jui Hsieh, Pradeep Ravikumar.
    In International Conference on Machine Learning (ICML), 2023
    [paper | code]

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

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

  • Order-free Learning Alleviating Exposure Bias in Multi-label Classification
    Che-Ping Tsai, Hung-Yi Lee.
    In AAAI Conference on Artificial Intelligence (AAAI), 2020.
    [paper| code]]

  • Completely Unsupervised Phoneme Recognition By A Generative Adversarial Network Harmonized with Iteratively Refined Hidden Markov Models
    Kuan-Yu Chen, Che-Ping Tsai, Da-Rong Liu, Hung-Yi Lee, Lin-shan Lee.
    In Interspeech, 2019.
    [paper | code]

  • Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification
    Che-Ping Tsai, Hung-Yi Lee.
    In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019.
    [paper | code]

  • Transcribing lyrics from commercial song audio: the first step towards singing content processing
    Che-Ping Tsai*, Yi-Lin Tuan, Hung-Yi Lee, Lin-shan Lee.
    *In International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2018.
    [paper | code]

Work experience

Awards

  • Silver Medal, 53rd International Mathematical Olympiad(IMO), Mar del Plata, Argentina, 2012.

  • Silver Medal, 52nd International Mathematical Olympiad(IMO), Amsterdam, Netherland, 2011.

Services