Publications
My up-to-date list of publications can be found at Google Scholar.
Preprints
T. T.-K. Lau and W. Su (2026). Symmetry-Compatible Matrix-Gradient Methods: Equivariant Updates, Spectral Operators, and Convergence. [pdf] [Optimization Online]
T. T.-K. Lau and W. Su (2026). Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers. [pdf] [arXiv] [code]
T. T.-K. Lau, Q. Long and W. Su (2025). PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective. [pdf] [arXiv] [code] [slides]
T. T.-K. Lau, W. Li, C. Xu, H. Liu and M. Kolar (2024). Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods. [pdf] [arXiv]
T. T.-K. Lau and H. Liu (2022). Wasserstein Distributionally Robust Optimization with Wasserstein Barycenters. [pdf] [arXiv]
Refereed Book Chapters
T. T.-K. Lau, H. Liu and T. Pock (2024). Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithms. In Alessandro Benfenati, Tatiana A. Bubba, Federica Porta, and Marco Viola, editors, Advanced Techniques in Optimization for Machine Learning and Imaging (ATOMI 2022), volume 61 of Springer INdAM Series, pages 83–149. Springer, Singapore, Springer INdAM Series. [URL] [pdf] [arXiv] [code]
Refereed Journal Publications
T. T.-K. Lau, H. Liu and M. Kolar (2026). AdAdaGrad: Adaptive Batch Size Schemes for Adaptive Gradient Methods. Statistical Learning and Data Science, Special issue on Statistics and AI, 100020. [URL] [arXiv] [code]
E. Chouzenoux, T. T.-K. Lau, C. Lefort, and J.-C. Pesquet (2019). Optimal Multivariate Gaussian Fitting with Applications to PSF Modeling in Two-Photon Microscopy Imaging. Journal of Mathematical Imaging and Vision, 61(7):1037–1050. [URL] [pdf]
Refereed Conference Publications
T. T.-K. Lau*, W. Li*, C. Xu, H. Liu and M. Kolar (2025). Adaptive Batch Size Schedules for Distributed Training of Language Models with Data and Model Parallelism. In the 2nd Conference on Parsimony and Learning (CPAL) (Proceedings Track). [pdf] [arXiv] [code]
T. T.-K. Lau and H. Liu (2022). Bregman Proximal Langevin Monte Carlo via Bregman–Moreau Envelopes. In Proceedings of the 39th International Conference on Machine Learning (ICML). [abs] [pdf] [arXiv] [code] [slides]
J. Zeng*, T. T.-K. Lau*, S. Lin, and Y. Yao (2019). Global Convergence of Block Coordinate Descent in Deep Learning. In Proceedings of the 36th International Conference on Machine Learning (ICML). [abs] [pdf] [arXiv] [code] [slides]
T. T.-K. Lau, E. Chouzenoux, C. Lefort, and J.-C. Pesquet (2018). Optimal Multivariate Gaussian Fitting for PSF Modeling in Two-photon Microscopy. In Proceedings of the IEEE International Symposium on Biomedical Imaging (ISBI 2018). [pdf]
*Equal contribution