Inexact proximal stochastic second-order methods for nonconvex composite optimization

DOI10.1080/10556788.2020.1713128zbMath1454.90066OpenAlexW3000160952WikidataQ126343631 ScholiaQ126343631MaRDI QIDQ5135256

Xiao Wang, Hongchao Zhang

Publication date: 19 November 2020

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/10556788.2020.1713128

zbMATH Keywords

complexityvariance reductionnonconvexsecond-order approximationstochastic gradientinexact subproblem solution(weakly) smooth functionproximal Polyak-Łojasiewicz (PL) inequality

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonconvex programming, global optimization (90C26)

Related Items (3)

An interior stochastic gradient method for a class of non-Lipschitz optimization problems ⋮ Unnamed Item ⋮ Variable metric proximal stochastic variance reduced gradient methods for nonconvex nonsmooth optimization

Uses Software

• ProxSARAH

Cites Work

• Unnamed Item
• Unnamed Item
• An inexact successive quadratic approximation method for L-1 regularized optimization
• A family of second-order methods for convex \(\ell _1\)-regularized optimization
• New results on subgradient methods for strongly convex optimization problems with a unified analysis
• Inexact proximal stochastic gradient method for convex composite optimization
• Conditional gradient type methods for composite nonlinear and stochastic optimization
• Proximal quasi-Newton methods for regularized convex optimization with linear and accelerated sublinear convergence rates
• Complexity bounds for primal-dual methods minimizing the model of objective function
• Accelerated first-order methods for large-scale convex optimization: nearly optimal complexity under strong convexity
• Generalized uniformly optimal methods for nonlinear programming
• Pathwise coordinate optimization
• Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization
• Proximal Newton-Type Methods for Minimizing Composite Functions
• Optimal methods of smooth convex minimization
• Stochastic Primal-Dual Coordinate Method for Regularized Empirical Risk Minimization
• Stochastic proximal quasi-Newton methods for non-convex composite optimization
• A Proximal Stochastic Gradient Method with Progressive Variance Reduction
• IMRO: A Proximal Quasi-Newton Method for Solving $\ell_1$-Regularized Least Squares Problems
• Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization

This page was built for publication: Inexact proximal stochastic second-order methods for nonconvex composite optimization