An accelerated first-order method for non-convex optimization on manifolds

DOI10.1007/s10208-022-09573-9arXiv2008.02252OpenAlexW3047120021MaRDI QIDQ6048700

Christopher Criscitiello, Nicolas Boumal

Publication date: 7 September 2023

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2008.02252

zbMATH Keywords

Riemannian manifoldcurvatureJacobi fieldfirst-order methodnon-convex optimizationoptimization on manifoldsaccelerated gradient descent

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) General theory of numerical analysis in abstract spaces (65J05) Abstract computational complexity for mathematical programming problems (90C60) Nonconvex programming, global optimization (90C26) Programming in abstract spaces (90C48) Real-valued functions on manifolds (58C05)

Related Items (1)

A Grassmann manifold handbook: basic geometry and computational aspects

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• First-order methods of smooth convex optimization with inexact oracle
• Adaptive cubic regularisation methods for unconstrained optimization. II: Worst-case function- and derivative-evaluation complexity
• Complete metrics of bounded curvature on noncompact manifolds
• Kantorovich's theorem on Newton's method in Riemannian manifolds
• Adaptive regularization with cubics on manifolds
• Fenchel duality theory and a primal-dual algorithm on Riemannian manifolds
• The Paulsen problem made simple
• Lower bounds for finding stationary points I
• A brief introduction to manifold optimization
• Lower bounds for finding stationary points II: first-order methods
• Iteration-complexity of gradient, subgradient and proximal point methods on Riemannian manifolds
• Cubic regularization of Newton method and its global performance
• Introduction to Riemannian Manifolds
• An Introduction to Optimization on Smooth Manifolds
• Global rates of convergence for nonconvex optimization on manifolds
• Conic Geometric Optimization on the Manifold of Positive Definite Matrices
• A Differential Geometric Approach to the Geometric Mean of Symmetric Positive-Definite Matrices
• A Short Proof of Berger's Curvature Tensor Estimates

This page was built for publication: An accelerated first-order method for non-convex optimization on manifolds