Practical Riemannian Neural Networks

by   Gaétan Marceau-Caron, et al.

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 These include the MNIST, SVHN, and FACE datasets as well as a previously unpublished electroencephalogram dataset.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.


page 1

page 2

page 3

page 4


Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics

Stochastic-gradient sampling methods are often used to perform Bayesian ...

Practical Quasi-Newton Methods for Training Deep Neural Networks

We consider the development of practical stochastic quasi-Newton, and in...

Fisher Information and Natural Gradient Learning of Random Deep Networks

A deep neural network is a hierarchical nonlinear model transforming inp...

Rieoptax: Riemannian Optimization in JAX

We present Rieoptax, an open source Python library for Riemannian optimi...

Efficient Quasi-Geodesics on the Stiefel Manifold

Solving the so-called geodesic endpoint problem, i.e., finding a geodesi...

Controlling Recurrent Neural Networks by Diagonal Conceptors

The human brain is capable of learning, memorizing, and regenerating a p...

Code Repositories


An extension to Torch7's nn package.

view repo

Please sign up or login with your details

Forgot password? Click here to reset