Data symmetries generically do not induce conserved quantities in NN training for analytic non-polynomial losses, but can for MSE with tensorizable networks.
June 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Derives exact equivariance conditions for augmented BNNs under variational inference and proposes orbit expansion symmetrization that outperforms baselines on equivariance and accuracy.
citing papers explorer
-
Conservation Laws from Data Symmetry in Neural Networks
Data symmetries generically do not induce conserved quantities in NN training for analytic non-polynomial losses, but can for MSE with tensorizable networks.
-
Equivariance and Augmentation for Bayesian Neural Networks
Derives exact equivariance conditions for augmented BNNs under variational inference and proposes orbit expansion symmetrization that outperforms baselines on equivariance and accuracy.