Yoav Gelberg

Yoav Gelberg

About Me

I'm a PhD student at the University of Oxford, supervised by Haggai Maron, Michael Bronstein and Yarin Gal. My research focuses on the symmetry and structure of neural network parameter spaces with application to deep (meta-)learning. I'm also interested in data symmetries more broadly and how structure can inform learning.

Before Oxford, I completed my undergraduate studies at the Technion as a Rothschild scholar, studied expander graphs at the Weizmann Institute, developed fair learning algorithms at Fairgen, and taught math and programming at the ARDC. My PhD is funded by the EPSRC through the AIMS CDT program.

Publications

* denotes equal contribution

LoL

Leaning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models

Theo (Moe) Putterman, Derek Lim, Yoav Gelberg, Stephanie Jegelka, Haggai Maron

Topological Blindspots

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Yam Eitan*, Yoav Gelberg*, Guy Bar-Shalom, Fabrizio Frasca, Michael Bronstein, Haggai Maron

Venue: ICLR 2025 (Oral Presentation 🎤)

KL Divergence

Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks

Yoav Gelberg, Tycho van der Ouderaa, Mark van der Wilk, Yarin Gal

Venue: GRaM Workshop @ ICML 2024 (Best Paper Award 🏆)