Zhu Li

Zhu Li

Kernel methods, Learning Theory, Fair Learning

I am currently a DPhil student supervised by Dino Sejdinovic. My primary interest is in scalable kernel method with Random Fourier Features and Nystrom Method with their theoretical properties. Currently I am trying to understand the possible connections between RFF with deep neural network along with their generalization and optimization property. I also did some research in fair learning.



  • Z. Li , A. Perez-Suay , G. Camps-Valls , D. Sejdinovic , Kernel Dependence Regularizers and Gaussian Processes with Applications to Algorithmic Fairness, ArXiv e-prints:1911.04322, 2019.
  • Z. Li , J. Ton , D. Oglic , D. Sejdinovic , Towards A Unified Analysis of Random Fourier Features, in International Conference on Machine Learning (ICML), 2019, PMLR 97:3905–3914.