Hongru Yang 杨鸿儒

I am a final year PhD candidate in Computer Science at The University of Texas at Austin, where I am extremely fortunate to be advised by Prof. Atlas Zhangyang Wang in the VITA research group. I am a visiting student at Princeton University from September 2023 to May 2025, hosted by Prof. Jason D. Lee. During my PhD study, I have worked closely with Prof. Yingbin Liang from The Ohio State University. Prior to my PhD study, I obtained my Bachelor degree in Statistics and Computer Science and Mathematics from University of Illinois Urbana-Champaign in 2019. My research interest mainly lies in deep learning theory and optimization.
I am looking for full-time opportunities.
selected publications
- Transformers Provably Learn Two-Mixture of Linear Classification via Gradient FlowThe Thirteenth International Conference on Learning Representations, 2025
- Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow AnalysisAdvances in Neural Information Processing Systems, 2024
- Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTKJournal of Machine Learning Research, 2024
- Pruning before training may improve generalizationJournal of Machine Learning Research, 2024
- On the neural tangent kernel analysis of randomly pruned neural networksIn International Conference on Artificial Intelligence and Statistics, 2023