[7] S. Na, H. Yang*. Curse of Dimensionality in Neural Network Optimization. [pdf]
[6] K. Chen, C. Yi, H. Yang. Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networks. [pdf]
[5] W. Hao^, C. Wang^*, X. Xu^, H. Yang^. Deep Learning via Neural Energy Descent. Communications in Computational Physics， 2025. [pdf]
[4] F. Liu, H. Yang, S. Hayou, Q. Li*, . From Optimization Dynamics to Generalization Bounds via Łojasiewicz Gradient Inequality. Transactions on Machine Learning Research, 2022. [pdf] [doi]
[3] S. Liang, S. W. Jiang, J. Harlim, H. Yang^*, Solving PDEs on Unknown Manifolds with Machine Learning. Applied and Computational Harmonic Analysis, 2024. [pdf] [doi]
[2] S. Liang^, L. Lyu^, C. Wang ^, H. Yang^*. Reproducing Activation Function for Deep Learning. Communication in Mathematical Sciences, 2024. [pdf] [doi]
[1] T. Luo^, H. Yang^*. Two-Layer Neural Networks for Partial Differential Equations: Optimization and Generalization Theory. In Siddhartha Mishra, Alex Townsend, Numerical Analysis meets Machine Learning (Handbook of Numerical Analysis, Volume 25), 1st Edition, 2024. [pdf] [doi]
^: Equal contribution; *: Corresponding author.