Rieoptax: Riemannian Optimization in JAX
Saiteja Utpala · Andi Han · Pratik Kumar Jawanpuria · Bamdev Mishra
Abstract
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.
Video
Chat is not available.
Successful Page Load