Optimization Dynamics of Equivariant and Augmented Neural Networks

03/23/2023
by   Axel Flinth, et al.
0

We investigate the optimization of multilayer perceptrons on symmetric data. We compare the strategy of constraining the architecture to be equivariant to that of using augmentation. We show that, under natural assumptions on the loss and non-linearities, the sets of equivariant stationary points are identical for the two strategies, and that the set of equivariant layers is invariant under the gradient flow for augmented models. Finally, we show that stationary points may be unstable for augmented training although they are stable for the equivariant models

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset