Unifying framework for accelerated randomized methods in convex optimization

DOI10.1007/978-3-031-30114-8_15arXiv1707.08486OpenAlexW3112239486MaRDI QIDQ6200198

Vladimir Zholobov, A. V. Gasnikov, Pavel Dvurechensky, Alexander Tyurin

Publication date: 22 March 2024

Published in: Foundations of Modern Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1707.08486

zbMATH Keywords

complexityconvex optimizationinexact oraclefirst-order methodszero-order methodsaccelerated gradient descent methodsaccelerated random block-coordinate descentaccelerated random derivative-free methodaccelerated random directional search

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Inexact coordinate descent: complexity and preconditioning
• First-order methods of smooth convex optimization with inexact oracle
• Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex
• Lectures on convex optimization
• Stochastic intermediate gradient method for convex problems with stochastic inexact oracle
• Universal method for stochastic composite optimization problems
• An optimal randomized incremental gradient method
• An accelerated directional derivative method for smooth stochastic convex optimization
• Oracle complexity separation in convex optimization
• A theoretical and empirical comparison of gradient approximations in derivative-free optimization
• Zeroth-order methods for noisy Hölder-gradient functions
• Gradient methods for problems with inexact model of the objective
• Accelerated and unaccelerated stochastic gradient descent in model generality
• Fast gradient descent for convex minimization problems with an oracle producing a \(( \delta, L)\)-model of function at the requested point
• Accelerated gradient-free optimization methods with a non-Euclidean proximal operator
• Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
• Random gradient-free minimization of convex functions
• Stochastic intermediate gradient method for convex optimization problems
• A stable alternative to Sinkhorn's algorithm for regularized optimal transport
• Efficiency of Coordinate Descent Methods on Huge-Scale Optimization Problems
• Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
• Stochastic Block Mirror Descent Methods for Nonsmooth and Stochastic Optimization
• Efficiency of the Accelerated Coordinate Descent Method on Structured Optimization Problems
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Smooth Optimization with Approximate Gradient
• Accelerated, Parallel, and Proximal Coordinate Descent
• Introduction to Derivative-Free Optimization
• Katyusha: the first direct acceleration of stochastic gradient methods
• Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise
• An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization
• Derivative-free optimization methods
• On Solving Large-Scale Polynomial Convex Problems by Randomized First-Order Algorithms
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Inexact model: a framework for optimization and variational inequalities
• Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization

This page was built for publication: Unifying framework for accelerated randomized methods in convex optimization