Publications

2024

1. Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis

   Hongru Yang, Bhavya Kailkhura, Zhangyang Wang, and Yingbin Liang

   Advances in Neural Information Processing Systems, 2024
2. Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK

   Hongru Yang, Ziyu Jiang, Ruizhe Zhang, Yingbin Liang, and Zhangyang Wang

   Journal of Machine Learning Research, 2024
3. Pruning before training may improve generalization

   Hongru Yang, Yingbin Liang, Xiaojie Guo, Lingfei Wu, and Zhangyang Wang

   Journal of Machine Learning Research, 2024

2023

1. On the neural tangent kernel analysis of randomly pruned neural networks

   Hongru Yang, and Zhangyang Wang

   In International Conference on Artificial Intelligence and Statistics, 2023

2021

1. Comparison of accuracy and scalability of gauss–Newton and alternating least squares for CANDECOMC/PARAFAC decomposition

   Navjot Singh, Linjian Ma, Hongru Yang, and Edgar Solomonik

   SIAM Journal on Scientific Computing, 2021

2020

1. Continuous regular functions

   Alexi Block Gorman, Philipp Hieronymi, Elliot Kaplan, Ruoyu Meng, Erik Walsberg, Zihe Wang, Ziqin Xiong, and Hongru Yang

   Logical Methods in Computer Science, 2020