My name is Chen Liu (刘晨). Welcome to my homepage!

I am interested in building reliable machine learning models. Particularly, I focus on deep neural networks and study it from an optimization perspective. Currently, my research focuses on:

  • Efficient algorithms to improve adversarial robustness.

  • Adaptive robustness against different categories of attacks.

  • Optimization and generalization properties of various robust learning methods.

In general, I am also interested in generative models, self-supervised learning and meta learning.

I am currently an assistant professor in the Department of Computer Science, City University of Hong Kong. I have several openings. If you are interested in working with me, please feel free to email me with your CV.

I obtained my Ph.D. degree from École Polytechnique Fédérale de Lausanne (EPFL) in August 2022 and was supervised by Prof. Sabine Süsstrunk and Dr. Mathieu Salzmann. My Ph.D. thesis is about verifiable, generalizable and efficient robust deep neural networks. I obtained my Master degree from École Polytechnique Fédérale de Lausanne (EPFL) in 2017 and Bachelor degree from Tsinghua University in 2015, both in Computer Science.

I was supported by Microsoft Research PhD Scholarship Programme from 2017 to 2019, working with Dr. Ryota Tomioka from Microsoft Research Cambridge. I worked at Swisscom Digital Lab in Lausanne, Switzerland in 2017 and Siemens Healthineers in Princeton, New Jersey, USA in 2016.

Last Update: September 2022
Page views since June 2019