Yang, Hongru

5 publications

JMLR 2025 Random Pruning Over-Parameterized Neural Networks Can Improve Generalization: A Training Dynamics Analysis Hongru Yang, Yingbin Liang, Xiaojie Guo, Lingfei Wu, Zhangyang Wang

ICLR 2025 Transformers Provably Learn Two-Mixture of Linear Classification via Gradient Flow Hongru Yang, Zhangyang Wang, Jason D. Lee, Yingbin Liang

JMLR 2024 Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK Hongru Yang, Ziyu Jiang, Ruizhe Zhang, Yingbin Liang, Zhangyang Wang

NeurIPS 2024 Training Dynamics of Transformers to Recognize Word Co-Occurrence via Gradient Flow Analysis Hongru Yang, Bhavya Kailkhura, Zhangyang Wang, Yingbin Liang

AISTATS 2023 On the Neural Tangent Kernel Analysis of Randomly Pruned Neural Networks Hongru Yang, Zhangyang Wang