A frequency-domain analysis of inexact gradient methods

DOI10.1007/s10107-021-01665-8zbMath1494.90078arXiv1912.13494OpenAlexW3164350488MaRDI QIDQ2149575

Oran Gannot

Publication date: 29 June 2022

Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.13494

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Convex programming (90C25) Frequency-response methods in control theory (93C80) Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory (93D05) Robust stability (93D09)

Related Items (2)

A nonlinear conjugate gradient method using inexact first-order information ⋮ Accelerated gradient methods with absolute and relative noise in the gradient

Uses Software

• PESTO
• Wirtinger Flow

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimized first-order methods for smooth convex minimization
• First-order methods of smooth convex optimization with inexact oracle
• Smooth strongly convex interpolation and exact worst-case performance of first-order methods
• On the convergence analysis of the optimized gradient method
• Lectures on convex optimization
• On the Kalman-Yakubovich-Popov lemma
• Resolvent estimates for spacetimes bounded by Killing horizons
• Exact worst-case convergence rates of the proximal gradient method for composite convex minimization
• On the worst-case complexity of the gradient method with exact line search for smooth strongly convex functions
• Analysis of biased stochastic gradient descent using sequential semidefinite programs
• Analytical convergence regions of accelerated gradient descent in nonconvex optimization under regularity condition
• Efficient first-order methods for convex minimization: a constructive approach
• Performance of first-order methods for smooth convex minimization: a novel approach
• Dissipative dynamical systems. I: General theory
• Dissipative dynamical systems. II: Linear systems with quadratic supply rates
• Proximal gradient flow and Douglas-Rachford splitting dynamics: global exponential stability via integral quadratic constraints
• Hybrid Deterministic-Stochastic Methods for Data Fitting
• Guaranteed Matrix Completion via Non-Convex Factorization
• Phase Retrieval via Wirtinger Flow: Theory and Algorithms
• Exponential Decay Rate Conditions for Uncertain Linear Systems Using Integral Quadratic Constraints
• A Less Conservative LMI Condition for Stability of Discrete-Time Systems With Slope-Restricted Nonlinearities
• Smooth Optimization with Approximate Gradient
• Analysis and Design of Optimization Algorithms via Integral Quadratic Constraints
• System analysis via integral quadratic constraints
• Analysis of Optimization Algorithms via Integral Quadratic Constraints: Nonstrongly Convex Problems
• Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach
• Worst-Case Convergence Analysis of Inexact Gradient and Newton Methods Through Semidefinite Programming Performance Estimation
• Operator Splitting Performance Estimation: Tight Contraction Factors and Optimal Parameter Selection
• Exact Worst-Case Performance of First-Order Methods for Composite Convex Optimization

This page was built for publication: A frequency-domain analysis of inexact gradient methods