Emergent Equivariance in Deep Ensembles
We demonstrate that deep ensembles are secretly equivariant models. More precisely, we
show that deep ensembles become equivariant for all inputs and at all training times by …
show that deep ensembles become equivariant for all inputs and at all training times by …
Ensembles provably learn equivariance through data augmentation
O Nordenfors, A Flinth - arxiv preprint arxiv:2410.01452, 2024 - arxiv.org
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 …
as the result of full augmentation in the limit of infinitely wide neural networks (neural tangent …
Symmetries in Overparametrized Neural Networks: A Mean-Field View
We develop a Mean-Field (MF) view of the learning dynamics of overparametrized Artificial
Neural Networks (NN) under data symmetric in law wrt the action of a general compact …
Neural Networks (NN) under data symmetric in law wrt the action of a general compact …