Categoria: <span>Reading Group</span>

Categoria: Reading Group

Events, Reading Group

Reading Group 17 Jan 2025

Paper: Equivariant Architectures for Learning in Deep Weight Spaces 🔗proceedings.mlr.press/v202/navon23a/navon23a.pdf Abstract: Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction. Unfortunately, the unique symmetry structure of deep weight spaces makes this design very challenging. If successful, such architectures would …