August
2017
Equivariance Through Parameter-Sharing
Authors:
Abstract:
We propose to study equivariance in deep neural networks through parameter symmetries. In particular, given a group G that acts discretely on the input and output of a standard neural network layer, we show that its equivariance is linked to the symmetry group of network parameters. We then propose two parameter-sharing scheme to induce the desirable symmetry on the parameters of the neural network. Under some conditions on the action of G, our procedure for tying the parameters achieves G-equivariance and guarantees sensitivity to all other permutation groups outside of G.
copied = false, 2000);
">
@conference{Ravanbaksh-2017-119742,
author = {S. Ravanbaksh And J. Schneider And B. Poczos},
title = {Equivariance Through Parameter-Sharing},
booktitle = {Proceedings of (ICML) International Conference on Machine Learning},
year = {2017},
month = {August},
pages = {2892 - 2901},
}
author = {S. Ravanbaksh And J. Schneider And B. Poczos},
title = {Equivariance Through Parameter-Sharing},
booktitle = {Proceedings of (ICML) International Conference on Machine Learning},
year = {2017},
month = {August},
pages = {2892 - 2901},
}