Research Areas
Optimization theory, algorithms, and their applications in data science.
Education
2014.08–2019.05 Ph.D., National University of Singapore
2010.08–2014.07 B.Sc., Tsinghua University
Work Experience
2026.09–present Associate Professor, Yau Mathematical Sciences Center, Tsinghua University
2025.04–2026.08 Associate Professor, Academy of Mathematics and Systems Science, Chinese Academy of Sciences
2021.10–2025.03 Assistant Professor, Academy of Mathematics and Systems Science, Chinese Academy of Sciences
2019.06–2021.09 Research Fellow, National University of Singapore
Publications
Meixia Lin and Yangjing Zhang. Low rank convex clustering for matrix-valued observations. SIAM Journal on Optimization, 36(3):1446–1475, 2026.
Shengxiang Deng, Xudong Li, and Yangjing Zhang. Alternating minimization for square root principal component pursuit. INFORMS Journal on Computing, published online, 2025.
Meixia Lin, Ziyang Zeng, and Yangjing Zhang. Multiple regression for matrix and vector predictors: models, theory, algorithms, and beyond. Electronic Journal of Statistics, 18(2):5563–5600, 2024.
Meixia Lin and Yangjing Zhang. DNNLasso: scalable graph learning for matrix-variate data. Proceedings of the 27th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR 238:316–324, 2024.
Yangjing Zhang, Ying Cui, Bodhisattva Sen, and Kim-Chuan Toh. On efficient and scalable computation of the nonparametric maximum likelihood estimator in mixture models. Journal of Machine Learning Research, 25(8):1–46, 2024.
Yangjing Zhang, Kim-Chuan Toh, and Defeng Sun. Learning graph Laplacian with MCP. Optimization Methods and Software, 39(3):569–600, 2024.
Shiwei Wang, Chao Ding, Yangjing Zhang, and Xinyuan Zhao. Strong variational sufficiency for nonlinear semidefinite programming and its implications. SIAM Journal on Optimization, 33(4):2988–3011, 2023.
Hong T. M. Chu, Kim-Chuan Toh, and Yangjing Zhang. On regularized square-root regression problems: distributionally robust interpretation and fast computations. Journal of Machine Learning Research, 23(308):1–39, 2022.
Ning Zhang, Yangjing Zhang, Defeng Sun, and Kim-Chuan Toh. An efficient linearly convergent regularized proximal point algorithm for fused multiple graphical Lasso problems. SIAM Journal on Mathematics of Data Science, 3(2):524–543, 2021.
Yangjing Zhang, Ning Zhang, Defeng Sun, and Kim-Chuan Toh. A proximal point dual Newton algorithm for solving group graphical Lasso problems. SIAM Journal on Optimization, 30(3):2197–2220, 2020.
Yangjing Zhang, Ning Zhang, Defeng Sun, and Kim-Chuan Toh. An efficient Hessian based algorithm for solving large-scale sparse group Lasso problems. Mathematical Programming, 179(1):223–263, 2020.
Preprints:
Shengxiang Deng, Xudong Li, and Yangjing Zhang. Exact low-dimensional reformulations for regularized spectral approximation. arXiv preprint arXiv:2608.27052, 2026.
Meixia Lin, Qian Zhang, and Yangjing Zhang. Fast joint graph Laplacian learning with nonconvex sparsity control. Submitted, 2026.
Meixia Lin, Ziyang Zeng, and Yangjing Zhang. Graph-guided fused regularization for single- and multi-task regression on spatiotemporal data. arXiv preprint arXiv:2602.14480, 2026.
Shengxiang Deng, Xudong Li, and Yangjing Zhang. Scalable kernel quantile regression: a preconditioned augmented Lagrangian method. arXiv preprint arXiv:2510.07929, 2025.
Yuexin Zhou, Chao Ding, and Yangjing Zhang. On some perturbation properties of nonsmooth optimization on Riemannian manifolds with applications. arXiv preprint arXiv:2308.06793, 2023.
