tensorflow-riemopt: A Library for Optimization on Riemannian Manifolds

2021/05/27 by Smirnov, Oleg
#Computational Geometry (cs.CG) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Mathematical Software (cs.MS)

paper · doi:10.48550/arxiv.2105.13921

Abstract

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

Related

• A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold
• Geomstats: A Python Package for Riemannian Geometry in Machine Learning
• geomstats: a Python Package for Riemannian Geometry in Machine Learning
• Riemannian Adaptive Optimization Algorithm and Its Application to Natural Language Processing
• CDOpt: A Python Package for a Class of Riemannian Optimization