activity
20242026
collaborators

10 papers

cs.LG2026

Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

Vincent Bürgin, Vincent Bürgin, Daniel Herbst +2

Many striking phenomena in deep learning, such as linear mode connectivity and the structured behavior of training dynamics, are closely tied to parameter symmetries: transformatio…

cs.LG2026

Neural Networks With Dense Weights Are Not Universal Approximators

Levi Rauchwerger, Stefanie Jegelka, Ron Levie

We investigate the approximation capabilities of dense neural networks. While universal approximation theorems establish that sufficiently large architectures can approximate arbit…

cs.LG2026

Learning to Approximate Uniform Facility Location via Graph Neural Networks

Chendi Qian, Christopher Morris, Stefanie Jegelka +1

Neural networks, particularly message-passing neural networks (MPNNs), are increasingly used as heuristics for hard combinatorial optimization problems. Yet many learning-based met…

cs.LG2026

Any-Subgroup Equivariant Networks via Symmetry Breaking

Abhinav Goel, Derek Lim, Hannah Lawrence +2

The inclusion of symmetries as an inductive bias, known as equivariance, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant archit…

cs.LG2025

Learning Linear Attention in Polynomial Time

Morris Yau, Ekin Akyürek, Jiayuan Mao +3

Previous research has explored the computational expressivity of Transformer models in simulating Boolean circuits or Turing machines. However, the learnability of these simulators…

cs.LG2025

Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs

Levi Rauchwerger, Stefanie Jegelka, Ron Levie

We analyze the universality and generalization of graph neural networks (GNNs) on attributed graphs, i.e., with node attributes. To this end, we propose pseudometrics over the spac…