publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Stochastic Gradient Descent on the Linear Bigram Model: Bias-Variance Scaling and Critical Batch Size
    Zeyu Bian, Dmitriy Drusvyatskiy, and Tianhao Wang
    In ICML Workshop on High-dimensional Learning Dynamics (HiLD), 2026
  2. Towards Understanding Momentum Acceleration in River-Valley Loss Landscape
    Miao Lu, Zeyu Bian, Kaiyue Wen, Beining Wu, and 3 more authors
    In Advances in Neural Information Processing Systems, 2026
  3. MIXPRS enables multi-population and multi-method polygenic risk scores using summary statistics
    Leqi Xu, Yikai Dong, Xiaowei Zeng, Zeyu Bian, and 3 more authors
    Nature Genetics, 2026