Noisy zeroth-order optimization for non-smooth saddle point problems

DOI10.1007/978-3-031-09607-5_2OpenAlexW4285199472MaRDI QIDQ2104286FDOQ2104286

Authors: Darina Dvinskikh, Vladislav Tominin, Iaroslav Tominin, Alexander V. Gasnikov 

Publication date: 7 December 2022

Full work available at URL: https://doi.org/10.1007/978-3-031-09607-5_2

Recommendations

• Zeroth-order methods for noisy Hölder-gradient functions
• Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small non-random noises
• Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points
• Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem
• One-point gradient-free methods for smooth and non-smooth saddle-point problems

zbMATH Keywords

stochastic optimizationgradient-free optimizationsaddle point problemsnon-smooth optimization

Mathematics Subject Classification ID

Stochastic programming (90C15) Minimax problems in mathematical programming (90C47) Derivative-free methods and methods using generalized derivatives (90C56)

Cites Work

• Lectures on modern convex optimization. Analysis, algorithms, and engineering applications
• Title not available (Why is that?)
• Introduction to Stochastic Search and Optimization
• Random gradient-free minimization of convex functions
• Online convex optimization in the bandit setting: gradient descent without a gradient
• Title not available (Why is that?)
• Introduction to Derivative-Free Optimization
• Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Universal method for stochastic composite optimization problems
• Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small non-random noises
• Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
• Safe global optimization of expensive noisy black-box functions in the \(\delta \)-Lipschitz framework
• Lectures on Stochastic Programming: Modeling and Theory, Third Edition
• On the upper bound for the expectation of the norm of a vector uniformly distributed on the sphere and the phenomenon of concentration of uniform measure on the sphere
• Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem

Cited In (8)

• Accelerated zero-order SGD method for solving the black box optimization problem under ``overparametrization condition
• Stochastic adversarial noise in the ``black box optimization problem
• Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs
• A Zeroth-Order Proximal Stochastic Gradient Method for Weakly Convex Stochastic Optimization
• Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods
• The ``black-box optimization problem: zero-order accelerated stochastic method via kernel approximation
• Zeroth-order nonconvex stochastic optimization: handling constraints, high dimensionality, and saddle points
• Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact

This page was built for publication: Noisy zeroth-order optimization for non-smooth saddle point problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2104286)