The Symmetries of Three-Layer ReLU Networks. Joint work with Moritz Grillo and Guido Montúfar.
Reducing Memorisation in Generative Models via Riemannian Bayesian Inference. Joint work with Albert Kjøller Jacobsen, Naima Elosegui Borras, Alejandro Valverde Mahou, and Georgios Arvanitidis.
Don’t Stop Me Yet: Sampling Loss Minima via Dissipative Riemannian Mechanics. Joint work with Albert Kjøller Jacobsen, Leo Uhre Jakobsen, and Georgios Arvanitidis.
Staying on the Manifold: Geometry-Aware Noise Injection. Joint work with Albert Kjøller Jacobsen and Georgios Arvanitidis, published in Proceedings of the 7th Northern Lights Deep Learning Conference (NLDL).
Compact Minimal Submanifolds of the Riemannian Symmetric Spaces SU(n)/SO(n), Sp(n)/U(n), SO(2n)/U(n), SU(2n)/Sp(n) via Complex-Valued Eigenfunctions. Joint work with Sigmundur Gudmundsson, published in Annals of Global Analysis and Geometry.
Master's Thesis: Minimal Submanifolds of the Classical Compact Riemannian Symmetric Spaces.
Bachelor's Thesis: CMC Tori in the Generalised Berger Spheres and their Duals.
From Pure Maths to Machine Learning – My journey from Lund to Lyngby.
I gave this presentation at the Math Student's Day 2025 in Lund, talking about my experience as a PhD student and my research. I am happy to send the slides to anyone who is interested.
