A Stochastic Levenberg--Marquardt Method Using Random Models with Complexity Results

DOI10.1137/20M1366253zbMath1487.49035arXiv1807.02176OpenAlexW3179632780MaRDI QIDQ5075237

Vyacheslav Kungurtsev, C. W. Royer, El Houcine Bergou, Youssef Diouane

Publication date: 10 May 2022

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1807.02176

zbMATH Keywords

machine learningLevenberg-Marquardt methodworst-case complexitydata assimilationnonlinear least squaresrandom modelsnoisy functions

Mathematics Subject Classification ID

Abstract computational complexity for mathematical programming problems (90C60) Derivative-free methods and methods using generalized derivatives (90C56) Numerical methods based on necessary conditions (49M05)

Related Items

A fully stochastic second-order trust region method ⋮ Convergence analysis of a subsampled Levenberg-Marquardt algorithm ⋮ TREGO: a trust-region framework for efficient global optimization ⋮ On the complexity of a stochastic Levenberg-Marquardt method ⋮ Adaptive Regularization Algorithms with Inexact Evaluations for Nonconvex Optimization

Uses Software

• EnKF
• DFO-GN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic derivative-free optimization using a trust region framework
• On the local convergence of a derivative-free algorithm for least-squares minimization
• Computation of sparse low degree interpolating polynomials and their application to derivative-free optimization
• A Levenberg-Marquardt method for large nonlinear least-squares problems with dynamic accuracy in functions and gradients
• Stochastic optimization using a trust-region method and random models
• Convergence and complexity analysis of a Levenberg-Marquardt algorithm for inverse problems
• A derivative-free Gauss-Newton method
• Convergence and evaluation-complexity analysis of a regularized tensor-Newton method for solving nonlinear least-squares problems
• A regularizing iterative ensemble Kalman method for PDE-constrained inverse problems
• Trust-Region Methods Without Using Derivatives: Worst Case Complexity and the NonSmooth Case
• Global complexity bound of the Levenberg–Marquardt method
• Ensemble Kalman methods for inverse problems
• On the Evaluation Complexity of Cubic Regularization Methods for Potentially Rank-Deficient Nonlinear Least-Squares Problems and Its Relevance to Constrained Nonlinear Optimization
• Convergence of Trust-Region Methods Based on Probabilistic Models
• Probability and Stochastics
• A Derivative-Free Algorithm for Least-Squares Minimization
• Levenberg--Marquardt Methods Based on Probabilistic Gradient Models and Inexact Subproblem Solution, with Application to Data Assimilation
• Introduction to Derivative-Free Optimization
• An Algorithm for Least-Squares Estimation of Nonlinear Parameters
• Nonlinear least squares — the Levenberg algorithm revisited
• Complexity and global rates of trust-region methods based on probabilistic models
• Optimization Methods for Large-Scale Machine Learning
• Inverse Problem Theory and Methods for Model Parameter Estimation
• Improving the Flexibility and Robustness of Model-based Derivative-free Optimization Solvers
• Tikhonov Regularization within Ensemble Kalman Inversion
• Adaptive regularisation for ensemble Kalman inversion
• A Nonmonotone Matrix-Free Algorithm for Nonlinear Equality-Constrained Least-Squares Problems
• Derivative-free optimization methods
• The ensemble Kalman filter for combined state and parameter estimation
• A method for the solution of certain non-linear problems in least squares

This page was built for publication: A Stochastic Levenberg--Marquardt Method Using Random Models with Complexity Results