Chairs & Committee
Find out who is behind this year’s conference.
Find out more
Kernel-based methods involve fundamental approximation theory (mathematics), stochastic analysis (statistics) and various applications from data science and machine learning. They are widely used in constructing mesh-free or high order methods for solving partial differential equations, high dimensional approximation, uncertainty quantification, density function estimation and machine (deep/kernel) learning. Recent advance in numerical analysis, statistical computing and learning theory brings fruitful results on kernel-based methods. The conference aims to provide a platform for experts and researchers on kernel methods with various backgrounds to work together in order to break research boundaries by exchanging ideas from various fields. It will provide a forum to announce research advancement, to discuss emerging research trends, to identify new research directions to promote applications of kernel methods on various fields and to deepen or stimulate fundamental research.
Themes of the conference themes include but not limited to
The past two conference were held in Guangzhou:
2017: International Conference of Kernel-based Approximation Methods in Machine Learning
2018: International Conference of Kernel-based Approximation Methods in Data Analysis