Currently a PhD candidate at the Technical University of Denmark (since Jan 2025), working with Prof. Søren Hauberg on geometric and Bayesian methods in neural networks. Previously a research assistant in the same lab, focusing on uncertainty quantification and identifiability. I’ve previously worked in MLE and Data Scientist roles, developing recommender systems and production-ready software. My background combines recent interests in applied mathematics, modeling and machine learning with previous experience in economics and finance gained through Research Assistant roles at the Danish Central Bank and BSc in Mathematics-Economics from the University of Copenhagen.
Syrota, S., Zainchkovskyy, Y., Xi, J., Bloem-Reddy, B., \& Hauberg, S. (2025). Identifying Metric Structures of Deep Latent Variable Models. Forty-Second International Conference on Machine Learning (ICML). Vancouver, Canada. July 13-19, 2025.
Syrota, S., Moreno-Muñoz, P. & Hauberg, S. (2024, October). Decoder ensembling for learned latent geometries. In Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM) at ICML 2024 (pp. 277-285). PMLR.