Rieoptax: Riemannian Optimization in JAX

We present Rieoptax, an open source Python library for Riemannian optimization in JAX. We show that many differential geometric primitives, such as Riemannian exponential and logarithm maps, are usually faster in Rieoptax than existing frameworks in Python, both on CPU and GPU. We support various ra...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Saiteja Utpala, Han, Andi, Jawanpuria, Pratik, Mishra, Bamdev
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 10.10.2022
Subjects
Differential geometry
Optimization
Riemann manifold
Online AccessGet full text

Cover

More Information
Summary:We present Rieoptax, an open source Python library for Riemannian optimization in JAX. We show that many differential geometric primitives, such as Riemannian exponential and logarithm maps, are usually faster in Rieoptax than existing frameworks in Python, both on CPU and GPU. We support various range of basic and advanced stochastic optimization solvers like Riemannian stochastic gradient, stochastic variance reduction, and adaptive gradient methods. A distinguishing feature of the proposed toolbox is that we also support differentially private optimization on Riemannian manifolds.
ISSN:2331-8422