General Hölder smooth convergence rates follow from specialized rates assuming growth bounds

DOI10.1007/s10957-023-02178-4OpenAlexW3155616566MaRDI QIDQ2696991

Benjamin Grimmer

Publication date: 17 April 2023

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

Full work available at URL: https://arxiv.org/abs/2104.10196

zbMATH Keywords

convergence ratesconvex optimizationfirst-order methodsgrowth/error boundsrestarting schemes

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25) Nonlinear programming (90C30)

Related Items (2)

Revisiting Spectral Bundle Methods: Primal-Dual (Sub)linear Convergence Rates ⋮ On optimal universal first-order methods for minimizing heterogeneous sums

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Primal-dual subgradient methods for convex problems
• Universal gradient methods for convex optimization problems
• New fractional error bounds for polynomial systems with applications to Hölderian stability in optimization and spectral theory of tensors
• Finite termination of the proximal point algorithm
• On gradients of functions definable in o-minimal structures
• On semi- and subanalytic geometry
• Introductory lectures on convex optimization. A basic course.
• Efficiency of proximal bundle methods
• From error bounds to the complexity of first-order descent methods for convex functions
• Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods
• Proximal level bundle methods for convex nondifferentiable optimization, saddle-point problems and variational inequalities
• New variants of bundle methods
• Restarting Frank-Wolfe: faster rates under Hölderian error bounds
• Rate of convergence of the bundle method
• Linear convergence of first order methods for non-strongly convex optimization
• Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization
• A simple nearly optimal restart scheme for speeding up first-order methods
• Weak Sharp Minima in Mathematical Programming
• Optimal methods of smooth convex minimization
• Monotone Operators and the Proximal Point Algorithm
• RSG: Beating Subgradient Method without Smoothness and Strong Convexity
• Sharpness, Restart, and Acceleration
• The Łojasiewicz Inequality for Nonsmooth Subanalytic Functions with Applications to Subgradient Dynamical Systems
• Minimization of unsmooth functionals

This page was built for publication: General Hölder smooth convergence rates follow from specialized rates assuming growth bounds