Convergence Analysis of Gradient Algorithms on Riemannian Manifolds without Curvature Constraints and Application to Riemannian Mass

DOI10.1137/19M1289285zbMath1457.53022arXiv1910.02280OpenAlexW3120367604WikidataQ115246909 ScholiaQ115246909MaRDI QIDQ5148408

Xiangmei Wang, Chong Li, Jin-Hua Wang, Jen-Chih Yao

Publication date: 4 February 2021

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1910.02280

zbMATH Keywords

global convergenceRiemannian manifoldsectional curvaturelinear convergencelocal convergencegradient algorithmRiemannian center of mass

Mathematics Subject Classification ID

Geodesics in global differential geometry (53C22) Global Riemannian geometry, including pinching (53C20) Mathematical programming (90C99)

Related Items

Fenchel conjugate via Busemann function on Hadamard manifolds ⋮ A trust region method for solving multicriteria optimization problems on Riemannian manifolds ⋮ Convergence of inexact steepest descent algorithm for multiobjective optimizations on Riemannian manifolds without curvature constraints ⋮ Incremental subgradient algorithms with dynamic step sizes for separable convex optimizations ⋮ On the relationship between the Kurdyka-Łojasiewicz property and error bounds on Hadamard manifolds ⋮ A Grassmann manifold handbook: basic geometry and computational aspects ⋮ Levitin-Polyak well-posedness by perturbations for the split hemivariational inequality problem on Hadamard manifolds

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic algorithms for computing means of probability measures
• Monotone and accretive vector fields on Riemannian manifolds
• Existence of solutions for variational inequalities on Riemannian manifolds
• Globally convergent optimization algorithms on Riemannian manifolds: Uniform framework for unconstrained and constrained optimization
• Minimizing a differentiable function over a differential manifold
• Characterizations of strict local minima and necessary conditions for weak sharp minima
• Unconstrained steepest descent method for multicriteria optimization on Riemannian manifolds
• Newton's method, zeroes of vector fields, and the Riemannian center of mass
• Convergence analysis of inexact proximal point algorithms on Hadamard manifolds
• Subgradient projection algorithms for convex feasibility on Riemannian manifolds with lower bounded curvatures
• Computing Riemannian center of mass on Hadamard manifolds
• Trust-region methods on Riemannian manifolds
• Steepest descent method with a generalized Armijo search for quasiconvex functions on Riemannian manifolds
• On the Convergence of Gradient Descent for Finding the Riemannian Center of Mass
• Riemannian $L^{p}$ center of mass: Existence, uniqueness, and convexity
• Riemannian median and its estimation
• Weak Sharp Minima in Mathematical Programming
• Variational Inequalities for Set-Valued Vector Fields on Riemannian Manifolds: Convexity of the Solution Set and the Proximal Point Algorithm
• Newton's method on Riemannian manifolds and a geometric model for the human spine
• Weak Sharp Minima on Riemannian Manifolds
• Linear Convergence of Subgradient Algorithm for Convex Feasibility on Riemannian Manifolds
• Monotone vector fields and the proximal point algorithm on Hadamard manifolds
• Locally Geodesically Quasiconvex Functions on Complete Riemannian Manifolds
• A.D. Alexandrov spaces with curvature bounded below
• Subgradient algorithms on Riemannian manifolds of lower bounded curvatures
• Second-order Sufficiency and Quadratic Growth for Nonisolated Minima
• Weak Sharp Minima: Characterizations and Sufficient Conditions
• Quotient Geometry with Simple Geodesics for the Manifold of Fixed-Rank Positive-Semidefinite Matrices
• Gradient Method for Optimization on Riemannian Manifolds with Lower Bounded Curvature
• Riemannian Geometry
• Newton's method on Riemannian manifolds: Smale's point estimate theory under the γ-condition
• The Gradient Projection Method Along Geodesics
• Geometry and spectra of compact Riemann surfaces
• Optimal stability and eigenvalue multiplicity