Grigorios Chrysos

Dr. Grigorios Chrysos is a faculty member in the Department of Electrical & Computer Engineering at the University of Wisconsin-Madison. His research focuses on reliable machine learning, emphasizing robustness to noise, out-of-distribution generalization, and theoretical understanding of neural/polynomial networks.

• Education:
  • PhD in Machine Learning, Imperial College London (2020)
  • M.Eng. in Electrical Engineering, National Technical University of Athens (2014)

Key research interests include robustness in deep networks, inductive bias analysis, and polynomial network design for high-order input interactions. His work explores adversarial robustness, fair model generalization, and extrapolation properties in generative frameworks.

Recent awards include the prestigious DAAD AInet Fellowship (2023), Best Reviewer Awards at NeurIPS (2022), ICLR (2022), and IMCL (2021), alongside Amazon Cloud Credits and Nvidia GPU donations (2019).

• Scientific Contributions:
  • Advancing tensor methods in machine learning
  • Developing polynomial networks for robustness
  • Designing efficient EEG seizure analysis algorithms