The symmetry increase that degrades equivariant networks on symmetric inputs is governed by a unique, computable 'symmetry infimum' determined by the feature space.
Topology from the differentiable viewpoint , isbn =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Reducing Symmetry Increase in Equivariant Neural Networks
The symmetry increase that degrades equivariant networks on symmetric inputs is governed by a unique, computable 'symmetry infimum' determined by the feature space.