My research focuses on the theoretical aspects of algorithms, computational geometry, and machine learning.
Papers
In the tradition of theoretical computer science, authors are listed in alphabetical order. Exceptions are marked with an asterisk (*), which indicates that the authors are listed by their level of contribution.
- Tight Bounds on the Hardness of Learning Simple Nonparametric Mixtures
Bryon Aragam, Wai Ming Tai
Conference on Learning Theory (COLT) 2023 - Learning Mixtures of Gaussians with Censored Data
Wai Ming Tai, Bryon Aragam *
International Conference on Machine Learning (ICML) 2023 - Optimal Coreset for Gaussian Kernel Density Estimation
Wai Ming Tai
Symposium on Computational Geometry (SOCG) 2022 - Optimal Estimation of Gaussian DAG Models
Ming Gao, Wai Ming Tai, Bryon Aragam *
International Conference on Artificial Intelligence and Statistics (AISTATS) 2022 - Finding an Approximate Mode of a Kernel Density Estimate
Jasper C.H. Lee, Jerry Li, Christopher Musco, Jeff M. Phillips, Wai Ming Tai
European Symposium on Algorithms (ESA) 2021 - The GaussianSketch for Almost Relative Error Kernel Distance
Jeff M. Phillips, Wai Ming Tai
International Conference on Randomization and Computation (RANDOM) 2020 - Approximate Guarantees for Dictionary Learning
Aditya Bhaskara, Wai Ming Tai
Conference on Learning Theory (COLT) 2019 - Near-Optimal Coresets of Kernel Density Estimates
Jeff M. Phillips, Wai Ming Tai
Symposium on Computational Geometry (SOCG) 2018 (Invited to DCG Special Issue)
Discrete & Computational Geometry (DCG) 2020 - Improved Coresets for Kernel Density Estimates
by Jeff M. Phillips, Wai Ming Tai
Symposium on Discrete Algorithms (SODA) 2018 - Tracking the Frequency Moments at All Times
Zengfeng Huang, Wai Ming Tai, Ke Yi
Unpublished
Academic Service
Reviewer for: ESA 2023, NeurIPS 2023, FOCS 2023, ICML 2023, SOCG 2023, STOC 2023, SODA 2023, NeurIPS 2022, ESA 2022, ICALP 2022, SOCG 2020, ESA 2019