You can also find my articles on my Google Scholar profile
Published in arXiv Preprint, 2023
We proposed two new notions of fairness when there exists uncertainty in the piorities. We also proposed two algorithms with certain guarantees of the proposed notion of fairness.
Recommended citation: Shen, Z., Wang, Z., Zhu, X., Fain, B., & Munagala, K. (2023). Fairness in the Assignment Problem with Uncertain Priorities. arXiv preprint arXiv:2301.13804. https://arxiv.org/abs/2301.13804
Published in arXiv Preprint, 2022
We conduct rigorous convergence analysis on a 2D model exhibiting both sharpness concentration and sharpness adaptivity phenomena.
Recommended citation: Zhu X., Wang Z., Wang, X., Zhou, M. and Ge, R., 2022. Understanding Edge-of-Stability Training Dynamics with a Minimalist Example. arXiv preprint arXiv:2210.03294. https://arxiv.org/abs/2210.03294
Published in arXiv Preprint, 2020
We make several new observations about the top eigenspace of layer-wise Hessians and explained the phenomena using Kronecker factorization. The insights also led to better explicit generalization bounds for neural nets.
Recommended citation: Wu, Y., Zhu, X., Wu, C., Wang, A. and Ge, R., 2020. Dissecting hessian: Understanding common structure of hessian in neural networks. arXiv preprint arXiv:2010.04261. https://arxiv.org/abs/2010.04261