Publications
* indicates equal contribution.
“RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization.”
The 43rd International Conference on Machine Learning (ICML 2026).
“Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks.”
The 43rd International Conference on Machine Learning (ICML 2026).
“Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis.”
The 37th International Conference on Algorithmic Learning Theory (ALT 2026) [Best Student Paper Award].
“Depth, Not Data: An Analysis of Hessian Spectral Bifurcation.”
2026 IEEE International Symposium on Information Theory (ISIT 2026) (Extended version in preparation for IEEE Transactions on Information Theory).
“HTMuon: Improving Muon via Heavy-Tailed Spectral Correction.”
Findings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026).
“KCES: Training-Free Defense for Robust Graph Neural Networks via Kernel Complexity.”
arXiv preprint.
“From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks.”
Transactions on Machine Learning Research (TMLR).
“A Statistical Estimator for the Topological Dimension of Compact Submanifolds in High-Dimensional Euclidean Spaces.”
Undergraduate Thesis (in Chinese) [Outstanding Graduation Thesis Award].
“A Mathematics Framework of Artificial Shifted Population Risk and Its Further Understanding Related to Consistency Regularization.”
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2024 (ECML 2024).