R-SPIDER: A Fast Riemannian Stochastic Optimization Algorithm with Curvature Independent Rate

11/10/2018
by   Jingzhao Zhang, et al.
0

We study smooth stochastic optimization problems on Riemannian manifolds. Via adapting the recently proposed SPIDER algorithm fang2018spider (a variance reduced stochastic method) to Riemannian manifold, we can achieve faster rate than known algorithms in both the finite sum and stochastic settings. Unlike previous works, by not resorting to bounding iterate distances, our analysis yields curvature independent convergence rates for both the nonconvex and strongly convex cases.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/09/2019

Nonconvex stochastic optimization on manifolds via Riemannian Frank-Wolfe methods

We study stochastic projection-free methods for constrained optimization...
research
02/22/2023

Faster Riemannian Newton-type Optimization by Subsampling and Cubic Regularization

This work is on constrained large-scale non-convex optimization where th...
research
04/06/2017

Accelerated Stochastic Quasi-Newton Optimization on Riemann Manifolds

We propose an L-BFGS optimization algorithm on Riemannian manifolds usin...
research
05/27/2020

Convergence Analysis of Riemannian Stochastic Approximation Schemes

This paper analyzes the convergence for a large class of Riemannian stoc...
research
06/29/2023

Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds

Numerous applications in machine learning and data analytics can be form...
research
06/07/2018

Towards Riemannian Accelerated Gradient Methods

We propose a Riemannian version of Nesterov's Accelerated Gradient algor...
research
03/13/2016

An efficient Exact-PGA algorithm for constant curvature manifolds

Manifold-valued datasets are widely encountered in many computer vision ...

Please sign up or login with your details

Forgot password? Click here to reset