tensorflow-riemopt: A Library for Optimization on Riemannian Manifolds
This library addresses the need for tools to implement and deploy geometric machine learning models, particularly for researchers and practitioners working with non-Euclidean data, but it is incremental as it builds on existing TensorFlow infrastructure.
The authors introduced tensorflow-riemopt, a Python library for optimization on Riemannian manifolds in TensorFlow, providing efficient implementations of manifold-constrained layers, geometric operations, and stochastic optimization algorithms to support research and production in geometric machine learning.
This paper presents tensorflow-riemopt, a Python library for geometric machine learning in TensorFlow. The library provides efficient implementations of neural network layers with manifold-constrained parameters, geometric operations on Riemannian manifolds, and stochastic optimization algorithms for non-Euclidean spaces. Designed for integration with TensorFlow Extended, it supports both research prototyping and production deployment of machine learning pipelines. The code and documentation are distributed under the MIT license and available at https://github.com/master/tensorflow-riemopt