DAI, Ben 戴奔

Position Assistant Professor
Email bendai [at] cuhk.edu.hk
ORCiD 0000-0002-1620-1021
Phone Number 3943 7928
Fax Number 2063 5188
Address LSB 117
Homepage https://www.bendai.org/

Academic Background

M.S. & Ph.D., City University of Hong Kong

Research Interest

Recent Publications

  • Wang, Z., & Dai, B. (2025). RankSEG-RMA: An efficient segmentation algorithm via reciprocal moment approximation. The Thirty-Ninth Conference on Neural Information Processing Systems (NeurIPS). arXiv GitHub
  • Dai, B. (2025). EnsLoss: Stochastic calibrated loss ensembles for preventing overfitting in classification. Proceedings of the Forty-Second International Conference on Machine Learning (ICML). arXiv GitHub
  • Gao, Y., & Dai, B. (2025). Word-level maximum mean discrepancy regularization for word embedding. Journal of the American Statistical Association (JASA). doi GitHub
  • Dai, B., & Li, C., Xue, H., Pan, W., & Shen, X. (2024). Inference of nonlinear causal effects with application to TWAS with GWAS summary data. Proceedings of the Third Conference on Causal Learning and Reasoning (CLeaR). pdf GitHub
  • Dai, B., & Qiu, Y. (2023). ReHLine: Regularized composite ReLU-ReHU loss minimization with linear computation and linear convergence. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS). pdf web GitHub
  • Dai, B., & Li, C. (2023). RankSEG: A consistent ranking-based framework for segmentation. Journal of Machine Learning Research (JMLR). html pdf GitHub

Professional Services

Research Grants

  • RGC-GRF 14304823 Principal Investigator
    Word-level maximum mean discrepancy: a kernel-based statistical regularization for text data
    2024-2026
  • RGC-ECS 24302422 Principal Investigator
    A statistical perspective on discriminative feature localization
    2023-2026