Chen Liu

Welcome to my homepage! I am a PhD candidate at the School of Computer and Communication Sciences (IC), École Polytechnique Fédérale de Lausanne (EPFL), supervised by Prof. Sabine Süsstrunk and co-supervised by Dr. Mathieu Salzmann. Previously, 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 am very fortunate to be supported by Microsoft Research PhD Scholarship Programme from September 2017 to April 2019, working with Dr. Ryota Tomioka from Microsoft Research Cambridge. From February to August 2017, I worked at Swisscom Digital Lab in Lausanne, Switzerland and completed my Master Thesis there. From July 2016 to February 2017, I did a research internship at Siemens Healthineers in Princeton, New Jersey, USA.

My research focus is on machine learning and optimization. I am particularly interested in deep learning, from theoretical understanding to practical applications. I am currently working on algorithms to build robust deep learning models that are certifiable, scalable and efficient.

Education

École Polytechnique Fédérale de Lausanne (EPFL)

Lausanne, Switzerland

Doctor of Philosophy in Computer Science

Sep 2017 -

Topic: Training and Tuning Deep Neural Networks: Faster, Stronger and Better

École Polytechnique Fédérale de Lausanne (EPFL)

Lausanne, Switzerland

Master of Science in Computer Science

Sep 2015 - Aug 2017

GPA: 5.73/6.00   Transcript

Tsinghua University

Beijing, P. R. China

Bachelor of Engineering in Computer Science

Aug 2011 - Jul 2015

GPA: 91.34/100.00   Transcript   Rank: 9/123

Publications

In reverse chronological order

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training Chen Liu, Zhichao Huang, Mathieu Salzmann, Tong Zhang, Sabine Süsstrunk. arXiv preprint: 2112.07324 [PDF]
Training Provably Robust Models by Polyhedral Envelope Regularization Chen Liu, Mathieu Salzmann, Sabine Süsstrunk. IEEE Transactions on Neural Networks and Learning Systems 2021. [PDF]   [Slides]   [Code]
On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them Chen Liu, Mathieu Salzmann, Tao Lin, Ryota Tomioka, Sabine Süsstrunk. Advances in Neural Information Processing Systems (NeurIPS) 2020. [PDF]   [Video]   [Poster]   [Slides]   [Code]
On Certifying Non-uniform Bounds against Adversarial Attacks Chen Liu, Ryota Tomioka, Volkan Cevher. International Conference on Machine Learning (ICML) 2019. [PDF]   [Video]   [Poster]   [Slides]   [Code]
Finding Mixed Nash Equilibria of Generative Adversarial Networks Ya-Ping Hsieh, Chen Liu, Volkan Cevher. International Conference on Machine Learning (ICML) 2019. [PDF]   [Video]   [Poster]   [Slides]
Consistent 3D Rendering in Medical Imaging Chen Liu, Shun Miao, Kaloian Petkov, Sandra Sudarsky, Daphne Yu, Tommaso Mansi. European Patent No. 18160956.1 [PDF]   [Metadata@EPO]

Awards & Honors

Qualcomm Innovation Fellowship Europe 2020 Finalist (15 in Europe)	Mar 2020
ICML 2019 Travel Award	Jun 2019
Microsoft Research PhD Scholarship	Sep 2017 - Apr 2019
Outstanding Graduates of Department of Computer Science and Technology in Tsinghua University	Jul 2015
Scholarship of Academic Excellence in Tsinghua University	Oct 2014
Scholarship of APEC Tsinghua CEO CCI	Oct 2013
Scholarship of Social Work in Tsinghua University	Oct 2013