tensorflow-riemopt: A Library for Optimization on Riemannian Manifolds

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Smirnov, Oleg
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917152112508928
author Smirnov, Oleg
author_facet Smirnov, Oleg
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2105_13921
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle tensorflow-riemopt: A Library for Optimization on Riemannian Manifolds
Smirnov, Oleg
Mathematical Software
Computational Geometry
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
title tensorflow-riemopt: A Library for Optimization on Riemannian Manifolds
topic Mathematical Software
Computational Geometry
Machine Learning
url https://arxiv.org/abs/2105.13921