* denotes equal contribution.

  • Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron
    Weihang Xu, Simon S. Du
    Conference on Learning Theory (COLT) 2023
    Oral presentation at High-dimensional learning dynamics workshop at ICML 2023

  • Combinatorial Bandits with Linear Constraints: Beyond Knapsacks and Fairness
    Qingsong Liu*, Weihang Xu*, Siwei Wang, Zhixuan Fang
    Conference on Neural Information Processing Systems (NeurIPS) 2022