4 papers
Quantitative Approximation Rates for Group Equivariant Learning
Jonathan W. Siegel, Snir Hordan, Hannah Lawrence +2
The universal approximation theorem establishes that neural networks can approximate any continuous function on a compact set. Later works in approximation theory provide quantitat…
To Augment or Not to Augment? Diagnosing Distributional Symmetry Breaking
Hannah Lawrence, Elyssa Hofgard, Vasco Portilheiro +3
Symmetry-aware methods for machine learning, such as data augmentation and equivariant architectures, encourage correct model behavior on all transformations (e.g. rotations or per…
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…
Improving Equivariant Networks with Probabilistic Symmetry Breaking
Hannah Lawrence, Vasco Portilheiro, Yan Zhang +1
Equivariance encodes known symmetries into neural networks, often enhancing generalization. However, equivariant networks cannot break symmetries: the output of an equivariant netw…