Lena Zellinger

PhD Student · University of Edinburgh, School of Informatics

I'm a third-year ELLIS PhD student at the University of Edinburgh, supervised by Antonio Vergari, Esmeralda S. Whitammer and Vincent Fortuin. I'm broadly interested in probabilistic inference and uncertainty quantification.

Your Name

Research interests

I’m interested in understanding when and why (!) approximate inference can be provably reliable. My main goal is to develop abstractions that shed light on the behavior of approximate inference and can inspire better solutions in practice. My current research focuses on variational inference, but I’m broadly interested in optimization, identifiability, information geometry, and obscure families of distributions!

Selected publications

Paper title
Even More Guarantees for Variational Inference in the Presence of Symmetries · NeurIPS 2026
Lena Zellinger & Antonio Vergari
Paper title
How to approximate inference with subtractive mixture models · AISTATS 2026
Lena Zellinger, Nicola Branchini, Lennert De Smet,
Víctor Elvira, Nikolay Malkin, Antonio Vergari