Yijun Dong (董一珺)

Research Interests

I am interested in randomized algorithms and the mathematical foundation of machine learning. My research focuses on computation- and data-efficient algorithms for high-dimensional problems in modern scientific computing and machine learning.

Selected Publications

• Does Weak-to-strong Generalization Happen under Spurious Correlations?
  Chenruo Liu*, Yijun Dong*, Qi Lei.
  ICLR 2026.
  

• Discrepancies are Virtue: Weak-to-Strong Generalization through Lens of Intrinsic Dimension.
  Yijun Dong, Yicheng Li, Yunai Li, Jason D. Lee, Qi Lei.
  ICML 2025.
  

• Robust Blockwise Random Pivoting: Fast and Accurate Adaptive Interpolative Decomposition.
  Yijun Dong, Chao Chen, Per-Gunnar Martinsson, Katherine Pearce.
  SIAM Journal on Matrix Analysis and Applications 2025. [GitHub]
  

• Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning.
  Yijun Dong*, Hoang Phan*, Xiang Pan*, Qi Lei.
  NeurIPS 2024. [GitHub]
  

• Sample Efficiency of Data Augmentation Consistency Regularization.
  Shuo Yang*, Yijun Dong*, Rachel Ward, Inderjit Dhillon, Sujay Sanghavi, Qi Lei.
  AISTATS 2023.
  

• Simpler is better: A comparative study of randomized algorithms for computing the CUR decomposition.
  Yijun Dong, Per-Gunnar Martinsson.
  Advances in Computational Mathematics 2023. [GitHub]
  

* denotes equal contribution or alphabetical order. For an updated list of my publications, please visit Google Scholar.

Education

Ph.D. in Computational Science, Engineering, and Mathematics, 2018 - 2023
Oden Institute for Computational Engineering and Sciences, UT Austin, Austin, Texas, US
Thesis: Randomized Dimension Reduction with Statistical Guarantees

B.S. in Applied Mathematics & Engineering Science, 2014 - 2018
Emory University, Atlanta, Georgia, US
Thesis: Crystals and Liquids in Gravitationally Confined Quasi-2-Dimensional Colloidal Systems