Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions

DOI10.1137/19M1244925zbMath1461.62145arXiv1805.10579MaRDI QIDQ5853717

Alireza Fallah, Necdet Serhat Aybat, Asuman Ozdaglar, Mert Gürbüzbalaban

Publication date: 11 March 2021

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1805.10579

zbMATH Keywords

convex optimization; stochastic approximation; matrix inequalities; Nesterov's method; robust control theory; accelerated methods

Mathematics Subject Classification ID

90C25: Convex programming

90C30: Nonlinear programming

90C15: Stochastic programming

93C10: Nonlinear systems in control theory

93C05: Linear systems in control theory

62L20: Stochastic approximation

Related Items

Unnamed Item, Unnamed Item, Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach, Differentially Private Accelerated Optimization Algorithms, Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent, Optimal Algorithms for Non-Smooth Distributed Optimization in Networks, Bounds for the tracking error of first-order online optimization methods, On strongly quasiconvex functions: existence results and proximal point algorithms, Generalized mirror prox algorithm for monotone variational inequalities: Universality and inexact oracle, Analytical convergence regions of accelerated gradient descent in nonconvex optimization under regularity condition, Relaxed-inertial proximal point type algorithms for quasiconvex minimization, Privacy-preserving dual stochastic push-sum algorithm for distributed constrained optimization

Uses Software

• CVX

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• First-order methods of smooth convex optimization with inexact oracle
• An optimal method for stochastic composite optimization
• Stochastic intermediate gradient method for convex problems with stochastic inexact oracle
• Parameter-dependent Lyapunov functions and the discrete-time Popov criterion for robust analysis
• Introductory lectures on convex optimization. A basic course.
• The risk-sensitive index and the \(H_ 2\) and \(H_ \infty\) norms for nonlinear systems
• Couplings and quantitative contraction rates for Langevin dynamics
• Adaptive restart for accelerated gradient schemes
• The robust H/sub 2/ control problem: a worst-case design
• Smooth Optimization with Approximate Gradient
• Analysis and Design of Optimization Algorithms via Integral Quadratic Constraints
• Acceleration of Stochastic Approximation by Averaging
• Analysis of Optimization Algorithms via Integral Quadratic Constraints: Nonstrongly Convex Problems
• Polynomial Roots from Companion Matrix Eigenvalues
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
• Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization, II: Shrinking Procedures and Optimal Algorithms
• A Stochastic Approximation Method