Projects point p on the manifold.

Exponential map of u at the origin.

Projects u on the tangent space of the origin.

Format metric in metric dict for logging.

Helper function to get dimension and activation at every layer. :param args: :return:

Logarithmic map of point p at the origin.

A workaround to respect strides of :code:`dest` when copying :code:`source` (https://github.com/geoopt/geoopt/issues/70) Parameters -

Exponential map of u at point p.

Row-normalize sparse matrix.

Performs a single optimization step. Arguments --------- closure : callable (optional) A closure that reevaluates

Adds a flag (and default value) to an ArgumentParser for each parameter in a config

Converts Euclidean Gradient to Riemannian Gradients.

Gets a directory to save the model. If the directory already exists, then append a new integer to the end of it. This method is useful so tha

Initializes random weigths on the manifold.

Inner product for tangent vectors at point x.

Logarithmic map of point p1 at point p2.

Adds points x and y.

Performs hyperboic martrix-vector multiplication.

Projects u on the tangent space of p.

Parallel transport of u from x to y.

Convert a scipy sparse matrix to a torch sparse tensor.

Squared distance between pairs of points.

Sparse version of GAT.