Stas Syrota - About
I am a first year PhD student 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-Economics at the University of Copenhagen (KU). In between the degrees, I had an explorative phase where I took a semester of a Statistics Master’s program at KU to study stochastic processes; and worked as a Machine Learning Engineer (recommender systems) and as a Data Scientist.
In general, I am interested in improving and developing machine learning methods that are theoretically sound and practically applicable. My research interests lie in the intersection of geometry, statistics, and machine learning, particularly in the context of deep generative models. I am currently focused on understanding the identifiability of latent variable models and the generalization properties of deep neural networks, with a strong emphasis on geometric approaches and Bayesian methods.
Apart from theoretical work, I am excited about applying machine learning to real-world problems, especially in the fields that require a geometric understanding of data or where uncertainty quantification is crucial.