LEE Ching-pei

• Associate Professor, Institute of Statistical Mathematics, Apr 2023 --.
• Associate Professor, Statistical Science Program, Graduate Institute for Advanced Studies, Graduate University for Advanced Studies (SOKENDAI), Apr 2023 --.
• Associate Professor, Department of Mathematical Informatics, Graduate School of Information Science and Technology, University of Tokyo, Sep 2026 --.

I am a faculty member at the Institute of Statistical Mathematics (ISM) and SOKENDAI. Starting this September, I will also be a faculty member of Mathematical Informatics at the University of Tokyo. Before these, I have been a tenure-track assistant research fellow at Academia Sinica and a Peng Tsu Ann Assistant Professor in the Department of Mathematics and the Institute for Mathematical Sciences at the National University of Singapore. Prior to that, I obtained my Ph.D in Computer Sciences with a minor in Mathematics at the University of Wisconsin-Madison. I work on nonlinear optimization and its applications, especially to large-scale problems.

I have an opening for a postdoc position (up to 5 years) in nonlinear optimization at the University of Tokyo starting from September 2026. See the details here.

I'm always looking for highly-motivated PhD students (SOKENDAI) and interns (ISM) to work on nonlinear optimization with me. For prospective PhD students, please also see the admission information here and the scholarship information here.

• Nonlinear optimization (problems involving real, as opposed to integer or discrete, variables): I'm mostly interested in algorithms that are efficient for large-scale real applications. This includes design and implementation of new algorithms, analysis of existing algorithms, study of specific problems, and nonsmooth analysis that helps us better understand the problems and algorithms
• Applications of nonlinear optimization: especially large-scale ones. Currently the major application I work on is practically efficient solvers for large-scale machine learning problems, but I am also open to other applications of optimization

Upcoming Travels/Presentations

• 2026 Apr. 17 - 27: Visiting Prof. Ting Kei Pong, PolyU, Hong Kong.
• 2026 Jun. 2 - 5: SIAM Conference on Optimization, Edinburgh, UK.
  • Presentation: Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Structured Neural Network

• Ching-pei Lee, Stephen J. Wright. Revisiting Superlinear Convergence of Proximal Newton-Like Methods to Degenerate Solutions, 2026.
• Jan Harold Alcantara, Ching-pei Lee, Akiko Takeda. A four-operator splitting algorithm for nonconvex and nonsmooth optimization. SIAM Journal on Optimization, 2025.
• Zih-Syuan Huang, Ching-pei Lee. Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network. The 38th Conference on Neural Information Processing Systems (NeurIPS), 2024. Pytorch implementation available in RAMDA.
• Jan Harold Alcantara, Ching-pei Lee. Accelerated projected gradient algorithms for sparsity constrained optimization problems The 36th Conference on Neural Information Processing Systems (NeurIPS), 2022.
• Ching-pei Lee, Ling Liang, Tianyun Tang, Kim-Chuan Toh. Accelerating nuclear-norm regularized low-rank matrix optimization through Burer-Monteiro decomposition. Journal of Machine Learning Research, 2024. MATLAB implementation available in BM-Global.
• Jan Harold Alcantara, Ching-pei Lee. Global convergence and acceleration of projection methods for feasibility problems involving union convex sets . Journal of Optimization Theory and Applications, 2025.
• Zih-Syuan Huang, Ching-pei Lee. Training Structured Neural Networks Through Manifold Identification and Variance Reduction. The 10th International Conference on Learning Representations (ICLR), 2022. Pytorch implementation available in RAMDA.
• Ching-pei Lee. Accelerating Inexact Successive Quadratic Approximation for Regularized Optimization Through Manifold Identification. Mathematical Programming, 2023. (Code.)
• Ching-pei Lee, Po-Wei Wang, Chih-Jen Lin. Limited-memory Common-directions Method for Large-scale Optimization: Convergence, Parallelization, and Distributed Optimization. Mathematical Programming Computation, 2022. Implementation available in MPI-LIBLINEAR. A preliminary version appeared in SDM 2017.
• Yu-Sheng Li, Wei-Lin Chiang, Ching-pei Lee. Manifold Identification for Ultimately Communication-Efficient Distributed Optimization. The 37th International Conference on Machine Learning (ICML), 2020. (Code.)
• Ching-pei Lee, Cong Han Lim, Stephen J. Wright. A Distributed Quasi-Newton Algorithm for Primal and Dual Regularized Empirical Risk Minimization, 2019. (Code for experiments in the paper.) A preliminary version appeared in KDD 2018.
• Ching-pei Lee, Stephen J. Wright. First-order algorithms converge faster than O(1/k) on convex problems. The 36th International Conference on Machine Learning (ICML), 2019.
• Ching-pei Lee, Stephen J. Wright. Inexact Variable Metric Stochastic Block-Coordinate Descent for Regularized Optimization. Journal of Optimization Theory and Applications, 2020.
• Ching-pei Lee, Stephen J. Wright. Inexact Successive Quadratic Approximation for Regularized Optimization. Computational Optimization and Applications, 2019.
• Stephen J. Wright, Ching-pei Lee. Analyzing Random Permutations for Cyclic Coordinate Descent. Mathematics of Computation, 2020.
• Ching-pei Lee, Kai-Wei Chang. Block-diagonal approximation for distributed dual regularized empirical risk minimization. Machine Learning, 2020. Implementation available in MPI-LIBLINEAR. (Code.) A preliminary version appeared in ICML 2015.
• Ching-pei Lee, Stephen J. Wright. Random Permutations Fix a Worst Case for Cyclic Coordinate Descent. the IMA Journal on Numerical Analysis, 2019.
• Po-Wei Wang, Ching-pei Lee, Chih-Jen Lin. The Common-directions Method for Regularized Empirical Risk Minimization. Journal of Machine Learning Research, 2019. (Supplementary mterials, code for experiments in the paper.)
• Tzu-Ming Kuo, Ching-pei Lee, Chih-Jen Lin. Large-scale Kernel RankSVM. SIAM International Conference on Data Mining, 2014. Implementation available in the LIBSVM extension for rankSVM. (Supplementary materials, code for experiments in the paper.)
• Wei-Cheng Chang, Ching-pei Lee, Chih-Jen Lin. A revisit to support vector data description (SVDD), 2015. Implementation available in the LIBSVM extension for SVDD.
• Ching-pei Lee, Chih-Jen Lin. Large-scale Linear RankSVM . Neural Computation, 2014. Implementation available in the LIBLINEAR extension for rankSVM. (Supplementary materials, code for experiments in the paper.)

• Solution Structure Utilization for Efficient Optimization and Large-scale Machine Learning.
• Revisiting Superlinear Convergence of Proximal Newton Methods to Degenerate Solutions .
• Training Structured Neural Networks Through Manifold Identification and Variance Reduction.

Software