Site in progress

Ochs Labs

Independent research in theoretical machine learning

Research on the theoretical foundations of machine learning — uncertainty quantification, model interpretability, and generalization in large language models.


Background

I'm Florian Ochs, an Oxford MSc Mathematical Sciences graduate (Distinction) working on the theoretical foundations of statistics and machine learning. My research experience spans probability metrics and generative model training dynamics, through internships at Luiss Guido Carli University (Rome) and Allianz (Munich).


Publications

[1]
Why Adversarial Diffusion Trains More Stably Than GANs: A Local Jacobian View Accepted (Poster), HiLD Workshop, ICML 2026 Read on OpenReview →