geomstats: a Python Package for Riemannian Geometry in Machine Learning

TL;DR

Geomstats is a Python package that facilitates Riemannian geometry computations on various manifolds, enabling advanced machine learning applications with efficient, GPU-accelerated, and user-friendly tools.

Contribution

The paper introduces geomstats, a comprehensive Python library for Riemannian geometry in machine learning, with implementations for multiple manifolds and integration into deep learning frameworks.

Findings

Efficient, unit-tested implementations for manifolds like hyperspheres and hyperbolic spaces.

Support for GPU acceleration and integration with Keras.

Provides Riemannian metrics, exponential/logarithm maps, and gradients for ML applications.

Abstract

We introduce geomstats, a python package that performs computations on manifolds such as hyperspheres, hyperbolic spaces, spaces of symmetric positive definite matrices and Lie groups of transformations. We provide efficient and extensively unit-tested implementations of these manifolds, together with useful Riemannian metrics and associated Exponential and Logarithm maps. The corresponding geodesic distances provide a range of intuitive choices of Machine Learning loss functions. We also give the corresponding Riemannian gradients. The operations implemented in geomstats are available with different computing backends such as numpy, tensorflow and keras. We have enabled GPU implementation and integrated geomstats manifold computations into keras deep learning framework. This paper also presents a review of manifolds in machine learning and an overview of the geomstats package with examples demonstrating its use for efficient and user-friendly Riemannian geometry.