Ben Dai

Assistant Professor at The Chinese University of Hong Kong.

profile.png

My name is Ben Dai (戴奔). I’m an Assistant Professor in the Department of Statistics at The Chinese University of Hong Kong. My primary research interests include statistical consistency, theory-driven machine learning methods, theoretical foundation of machine learning, black-box significance testing, statistical computing and software development.

news

Sep 1, 2024 I recently published a preprint on ensemble learning with calibrated losses. For further details, please refer to the arXiv and GitHub links.
Jan 1, 2024 I am currently engaged in the SToAT project, where we are recruiting students to work as short-term RAs for the development of open-source statistical toolkits.
Nov 6, 2023 The ML algorithm ReHLine that we recently developed has been accepted for publication at NeurIPS 2023.

selected publications [all papers]

  1. Arxiv
    EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification
    Ben Dai
    Arxiv, 2024
  2. NeurIPS
    ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence
    Ben Dai*, and Yixuan Qiu*
    In Thirty-seventh Conference on Neural Information Processing Systems, 2023
  3. JMLR
    RankSEG: A Consistent Ranking-based Framework for Segmentation
    Ben Dai, and Chunlin Li
    Journal of Machine Learning Research, 2023
  4. TNNLS
    Significance tests of feature relevance for a black-box learner
    Ben Dai, Xiaotong Shen, and Wei Pan
    IEEE Transactions on Neural Networks and Learning Systems, 2022