Ensembles provably learn equivariance through data augmentation

Understand

Recently, it was proved that group equivariance emerges in ensembles of neural networks as the result of full augmentation in the limit of infinitely wide neural networks (neural tangent kernel limit).

• In this paper, we extend this result significantly.
• We provide a proof that this emergence does not depend on the neural tangent kernel limit at all.
• We also consider stochastic settings, and furthermore general architectures.