Some unified theory for variance reduced prox-linear methods

DOI10.1137/25M1727606MaRDI QIDQ7313360zbMATH OpenFDO

Authors Benjamin Grimmer, Yue Wu

Publication date 13 August 2026

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

Full work available at URL https://doi.org/10.1137/25M1727606

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Stochastic programming (90C15) Nonconvex programming, global optimization (90C26) Nonlinear programming (90C30)

Cites work

• A Gauss-Newton method for convex composite optimization
• A proximal method for composite minimization
• Accelerating Stochastic Composition Optimization
• An introduction to matrix concentration inequalities
• Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization
• Efficiency of minimizing compositions of convex functions and smooth maps
• Error bounds, quadratic growth, and linear convergence of proximal methods
• scientific article; zbMATH DE number 7370566 (Why is no real title available?)
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
• Modified Gauss–Newton scheme with worst case guarantees for global performance
• On the evaluation complexity of composite function minimization with applications to nonconvex nonlinear programming
• Stochastic composition optimization of functions without Lipschitz continuous gradient
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Stochastic model-based minimization of weakly convex functions
• Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization
• User-friendly tail bounds for sums of random matrices
• Variance reduction for root-finding problems

This page was built for publication: Some unified theory for variance reduced prox-linear methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7313360)