Understanding Riemannian Acceleration via a Proximal Extragradient Framework

2021/11/04 by Jin, Jikai, Sra, Suvrit · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)

paper · doi:10.48550/arxiv.2111.02763

Abstract

We contribute to advancing the understanding of Riemannian accelerated gradient methods. In particular, we revisit Accelerated Hybrid Proximal Extragradient(A-HPE), a powerful framework for obtaining Euclidean accelerated methods \citepmonteiro2013accelerated. Building on A-HPE, we then propose and analyze Riemannian A-HPE. The core of our analysis consists of two key components: (i) a set of new insights into Euclidean A-HPE itself; and (ii) a careful control of metric distortion caused by Riemannian geometry. We illustrate our framework by obtaining a few existing and new Riemannian accelerated gradient methods as special cases, while characterizing their acceleration as corollaries of our main results.

Cited by

• A Riemannian Accelerated Proximal Gradient Method

Related

• Riemannian accelerated gradient methods via extrapolation
• From Nesterov's Estimate Sequence to Riemannian Acceleration
• A Riemannian Accelerated Proximal Gradient Method
• Towards Riemannian Accelerated Gradient Methods
• Riemannian Proximal Gradient Methods (extended version)