Dr Fanghui Liu

Research Interests:

  • Machine learning 
  • Kernel methods
  • Learning Theory

 

Biography

Dr Fanghui Liu is currently an Assistant Professor at the University of Warwick, UK. He received the B.E. degree in Automation from Harbin Institute of Technology, China, and the Ph.D. degree from Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, China, in 2014 and 2019, respectively. Before joining in LIONS Lab in October 2021 in EPFL, he worked as a postdoc researcher in ESAT-STADIUS, KU Leuven, Belgium from Oct. 2019 to Sep. 2021. His research areas mainly include machine learning, kernel methods, and learning theory.

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

J. Ye†; Z. Zhu; F. Liu; R. Shokri; V. Cevher 

2023. 37th Annual Conference on Neural Information Processing Systems, New Orleans, USA, December 10-16. 2023.

On the Convergence of Encoder-only Shallow Transformers

Y. Wu; F. Liu; G. Chrysos; V. Cevher 

2023. 37th Annual Conference on Neural Information Processing Systems, New Orleans, USA, December 10-16. 2023.

Benign Overfitting in Deep Neural Networks under Lazy Training

Z. Zhu; F. Liu; G. Chrysos; F. Locatello; V. Cevher 

2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July, 23-29, 2023.

What can online reinforcement learning with function approximation benefitfrom general coverage conditions

F. Liu; L. Viano; V. Cevher 

2023. 40th International Conference on Machine Learning (ICML), Honolulu, Hawaii, USA, July, 23-29, 2023.

Federated Learning under Covariate Shifts with Generalization Guarantees

A. Ramezani-Kebrya; F. Liu; T. M. Pethick; G. Chrysos; V. Cevher 

Transactions on Machine Learning Research. 2023. num. 06.

Contact

e-mail address: [email protected]


Access map