Zeroth-order methods for noisy Hölder-gradient functions

DOI10.1007/s11590-021-01742-zzbMath1497.90156arXiv2006.11857OpenAlexW3157347217MaRDI QIDQ2162695

Pavel Dvurechensky, Innokentiy Shibaev, Alexander V. Gasnikov

Publication date: 9 August 2022

Published in: Optimization Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.11857

zbMATH Keywords

inexact oraclenon-convex problemgradient-free methodszeroth-order optimization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26)

Related Items (5)

Oracle complexity separation in convex optimization ⋮ Generalized mirror prox algorithm for monotone variational inequalities: Universality and inexact oracle ⋮ An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization ⋮ Unifying framework for accelerated randomized methods in convex optimization ⋮ Recent Theoretical Advances in Non-Convex Optimization

Uses Software

• BRENT
• DiffSharp
• NESUN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Universal gradient methods for convex optimization problems
• A theoretical and empirical comparison of gradient approximations in derivative-free optimization
• Random gradient-free minimization of convex functions
• Introduction to Derivative-Free Optimization
• Introduction to Stochastic Search and Optimization
• Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise
• Derivative-free optimization methods
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Stochastic Approximation of Minima with Improved Asymptotic Speed
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization

This page was built for publication: Zeroth-order methods for noisy Hölder-gradient functions