Dr Grigorios Chrysos

Research Interests:

  • Polynomial neural networks
  • Tensor decomposition
  • Tensor analysis
  • Generative models
  • Machine learning

 

Biography

Grigorios is currently an Assistant Professor at University of Wisconsin-Madison, USA. He obtained his master’s degree in Electrical, Electronic Engineering and Computer Science from the National Technical University of Athens in 2014. Sequentially, he pursued a PhD degree at Imperial College London. He was a post-doctoral researcher with the Laboratory for Information and Inference Systems at the École Polytechnique Fédérale de Lausanne (EPFL), Switzerland.

Publications with LIONS

Learning to Remove Cuts in Integer Linear Programming

P. Puigdemont; E. P. Skoulakis; G. Chrysos; V. Cevher 

2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.

Detailed record

Full text

Robust NAS under adversarial training: benchmark, theory, and beyond

Y. Wu; F. Liu; C-J. Simon-Gabriel; G. Chrysos; V. Cevher 

2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.

Detailed record

Full text

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Y. Chen; F. Liu; Y. Lu; G. Chrysos; V. Cevher 

2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.

Detailed record

Full text

Revisiting Character-level Adversarial Attacks for Language Models

E. Abad Rocamora; Y. Wu; F. Liu; G. Chrysos; V. Cevher 

2024. 41st International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024.

Detailed record

Full text

Efficient local linearity regularization to overcome catastrophic overfitting

E. Abad Rocamora; F. Liu; G. Chrysos; P. M. Olmos; V. Cevher 

2024. 12th International Conference on Learning Representations (ICLR 2024), Vienna, Austria, May 7-11, 2024.

Detailed record

Full text

Contact

e-mail address: Grigorios Chrysos

EPFL people page

Access map