pith. sign in

arxiv: 1602.08007 · v1 · pith:FKNMNEFFnew · submitted 2016-02-25 · 💻 cs.NE · cs.LG· stat.ML

Practical Riemannian Neural Networks

classification 💻 cs.NE cs.LGstat.ML
keywords gradientriemanniandescentsnetworksneuralquasi-diagonaldatasetssimple
0
0 comments X
read the original abstract

We provide the first experimental results on non-synthetic datasets for the quasi-diagonal Riemannian gradient descents for neural networks introduced in [Ollivier, 2015]. These include the MNIST, SVHN, and FACE datasets as well as a previously unpublished electroencephalogram dataset. The quasi-diagonal Riemannian algorithms consistently beat simple stochastic gradient gradient descents by a varying margin. The computational overhead with respect to simple backpropagation is around a factor $2$. Perhaps more interestingly, these methods also reach their final performance quickly, thus requiring fewer training epochs and a smaller total computation time. We also present an implementation guide to these Riemannian gradient descents for neural networks, showing how the quasi-diagonal versions can be implemented with minimal effort on top of existing routines which compute gradients.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.