Riemannian stochastic variance-reduced cubic regularized Newton method for submanifold optimization

DOI10.1007/s10957-022-02137-5OpenAlexW4311546540MaRDI QIDQ2679570

Sam Davanloo Tajbakhsh, Dewei Zhang

Publication date: 23 January 2023

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2010.03785

zbMATH Keywords

stochastic optimizationvariance reductionRiemannian optimizationcubic regularizationmanifold optimization

Mathematics Subject Classification ID

Stochastic programming (90C15) Methods of quasi-Newton type (90C53) Programming in abstract spaces (90C48)

Related Items

Riemannian Natural Gradient Methods

Uses Software

• Manopt

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new approach to the proximal point method: convergence on general Riemannian manifolds
• Adaptive cubic regularisation methods for unconstrained optimization. I: Motivation, convergence and numerical results
• Adaptive cubic regularisation methods for unconstrained optimization. II: Worst-case function- and derivative-evaluation complexity
• Complexity bounds for second-order optimality in unconstrained optimization
• Minimizing a differentiable function over a differential manifold
• Subgradient algorithm on Riemannian manifolds
• A brief introduction to manifold optimization
• A collection of nonsmooth Riemannian optimization problems
• Iteration-complexity of gradient, subgradient and proximal point methods on Riemannian manifolds
• Trust-region methods on Riemannian manifolds
• Matrix concentration inequalities via the method of exchangeable pairs
• On the complexity of finding first-order critical points in constrained nonlinear optimization
• Cubic regularization of Newton method and its global performance
• Riemannian Trust Regions with Finite-Difference Hessian Approximations are Globally Convergent
• Optimization Methods on Riemannian Manifolds and Their Application to Shape Space
• Manopt, a Matlab toolbox for optimization on manifolds
• Adaptive Quadratically Regularized Newton Method for Riemannian Optimization
• Recent Advances in Stochastic Riemannian Optimization
• An implicit trust-region method on Riemannian manifolds
• Optimization Techniques on Riemannian Manifolds
• Proximal Point Algorithm On Riemannian Manifolds
• Probability
• Introduction to Riemannian Manifolds
• Multivariate T-Distributions and Their Applications
• Proximal point method for a special class of nonconvex functions on Hadamard manifolds
• Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods
• An Introduction to Optimization on Smooth Manifolds
• Methods for Sparse and Low-Rank Recovery under Simplex Constraints
• Global rates of convergence for nonconvex optimization on manifolds
• Riemannian Optimization and Its Applications
• Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold
• Riemannian Stochastic Variance Reduced Gradient Algorithm with Retraction and Vector Transport
• Gradient Descent Finds the Cubic-Regularized Nonconvex Newton Step
• Gradient Method for Optimization on Riemannian Manifolds with Lower Bounded Curvature
• A new, globally convergent Riemannian conjugate gradient method
• Conic Geometric Optimization on the Manifold of Positive Definite Matrices
• Stochastic Gradient Descent on Riemannian Manifolds
• The Gradient Projection Method Along Geodesics