Yijun Dong (董一珺)

Courant Instructor/Assistant Professor (postdoc) Courant Institute of Mathematical Sciences New York University Email: yd1319 [@] nyu [DOT] edu Office: WWH 526, 251 Mercer St, New York, NY 10012

About Me

I am a Courant Instructor/Assistant Professor (postdoc) at the Courant Institute of New York University. I completed my PhD at the Oden Institute of UT Austin, advised by Prof. Per-Gunnar Martinsson and Prof. Rachel Ward.

My research lies in randomized numerical linear algebra and learning theory. Specifically, I am interested in the computational and sample efficiency of algorithms in machine learning and scientific computing. From the computational efficiency perspective, my work is centered on matrix sketching and randomized low-rank decompositions like SVD and CUR. From the sample efficiency perspective, my work focuses on the generalization and distributional robustness of learning algorithms in data-limited settings.

(Curriculum Vitae, Google Scholar, GitHub)

News

• 2024/09: Our paper got accepted at NeurIPS 2024: Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning with Hoang Phan, Xiang Pan, Qi Lei.

• 2024/06: Our paper got accepted at SIAM Journal on Matrix Analysis and Applications: Efficient Bounds and Estimates for Canonical Angles in Randomized Subspace Approximations with Per-Gunnar Martinsson, Yuji Nakatsukasa.

• 2023/09: Our paper got accepted at NeurIPS 2023: Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering with Kevin Miller, Qi Lei, Rachel Ward.

• 2023/04: Our paper got accepted at ICML 2023: Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift with Yuege Xie, Rachel Ward.

• 2023/03: I defended my thesis on ‘‘Randomized Dimension Reduction with Statistical Guarantees’’ at UT Austin. [dissertation, slides]

Selected Recent Works

(* denotes equal contribution or alphabetical order)

1. Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
   Yijun Dong*, Hoang Phan*, Xiang Pan*, Qi Lei
   Neural Information Processing Systems (NeurIPS), 2024. [GitHub]
   

2. Robust Blockwise Random Pivoting: Fast and Accurate Adaptive Interpolative Decomposition
   Yijun Dong, Chao Chen, Per-Gunnar Martinsson, Katherine Pearce, 2023. [GitHub]
   

3. Efficient Bounds and Estimates for Canonical Angles in Randomized Subspace Approximations
   Yijun Dong, Per-Gunnar Martinsson, Yuji Nakatsukasa
   SIAM Journal on Matrix Analysis and Applications, 2024. [GitHub]
   

4. Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering
   Yijun Dong*, Kevin Miller*, Qi Lei, Rachel Ward
   Neural Information Processing Systems (NeurIPS), 2023. [GitHub]
   

5. Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift
   Yijun Dong*, Yuege Xie*, Rachel Ward
   International Conference on Machine Learning (ICML), 2023. [GitHub, poster]
   

6. Sample Efficiency of Data Augmentation Consistency Regularization
   Shuo Yang*, Yijun Dong*, Rachel Ward, Inderjit Dhillon, Sujay Sanghavi, Qi Lei
   International Conference on Artificial Intelligence and Statistics (AISTATS), 2023. [pmlr]
   

7. 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]
   

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