Anastasis Kratsios
Profile Photo
Assistant Professor
HH 416
(905) 525 9140 ext. 27304
(905) 522-0935

I develop and study universal deep learning models capable of leveraging geometric structures in mathematical finance and data science problems.

Financial Mathematics, Geometric Deep Learning, Foundations of Artificial Intelligence

MFM 703
MFM 713

A. Kratsios, L. Papon: Universal Approximation Theorems for Differentiable Geometric Deep Learning, JMLR - Journal of Machine Learning Research, 2022.
A. Kratsios, B. Zamanlooy, I. Dokmanic, T. Liu: Universal Approximation Under Constraints is Possible with Transformers, ICLR - International Conference on Learning Representations, 2022 Spotlight.
A. Kratsios and C. Hyndman: NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation, JMLR - Journal of Machine Learning Research - Volume 22, 2021.

Go Back
McMaster University - Faculty of Science | Math & Stats