Stas Syrota - About

I am a first year PhD candidate at the Technical University of Denmark (DTU), supervised by Søren Hauberg. Prior to this, I completed a Master’s degree in Mathematical Modeling and Computing at DTU and a Bachelor’s degree in Mathematics at the University of Copenhagen (KU).

In general, I am interested in applying Geometry and Bayesian probability to all things Deep Learning. My current research is concerned with fundamental machine learning theory applying geometry to understand the generalization properties of deep neural networks and statistical identifiability guarantees of Deep Latent Variable Models. Apart from this I am excited to explore applications of these methods to meaningful real-world problems.

Outside of academia, I have worked as a Machine Learning Engineer, training and deploying transformer-based models for personalized search and recommendation systems. I also have experience as a Data Scientist at a pension institute, applying machine learning techniques to create software advising customers on insurance and pension.