A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization

DOI10.1137/20M1312952zbMath1470.90096arXiv2001.10669OpenAlexW3174976469MaRDI QIDQ4995000

Ruszczyński, Andrzej

Publication date: 22 June 2021

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

Full work available at URL: https://arxiv.org/abs/2001.10669

zbMATH Keywords

nonsmooth optimizationstochastic approximationstochastic variational inequalityrisk-averse optimizationstochastic composition optimization

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Nonsmooth analysis (49J52) Stochastic approximation (62L20)

Related Items (7)

A stochastic subgradient method for distributionally robust non-convex and non-smooth learning ⋮ Stochastic Multilevel Composition Optimization Algorithms with Level-Independent Convergence Rates ⋮ Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems ⋮ Subgradient Sampling for Nonsmooth Nonconvex Minimization ⋮ Stochastic composition optimization of functions without Lipschitz continuous gradient ⋮ Mini-Batch Risk Forms ⋮ Distributed stochastic compositional optimization problems over directed networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
• Generalized gradients of Lipschitz functionals
• Stochastic approximation methods for constrained and unconstrained systems
• From stochastic dominance to mean-risk models: Semideviations as risk measures
• Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization
• Stochastic subgradient method converges on tame functions
• Statistical estimation of composite risk functionals and risk optimization problems
• Coherent Measures of Risk
• Curves of Descent
• A Linearization Method for Nonsmooth Stochastic Programming Problems
• Clarke Subgradients of Stratifiable Functions
• Lectures on Stochastic Programming
• Generalized Gradients and Applications
• Analysis of recursive stochastic algorithms
• Semismooth and Semiconvex Functions in Constrained Optimization
• Stochastic Methods for Composite and Weakly Convex Optimization Problems
• Stochastic Model-Based Minimization of Weakly Convex Functions
• Multilevel Stochastic Gradient Methods for Nested Composition Optimization
• Accelerating Stochastic Composition Optimization
• A Single Timescale Stochastic Approximation Method for Nested Stochastic Optimization
• Stochastic Approximations and Differential Inclusions
• Regularized Iterative Stochastic Approximation Methods for Stochastic Variational Inequality Problems
• Stochastic Approximations and Differential Inclusions, Part II: Applications
• Sample Average Approximation Method for Compound Stochastic Optimization Problems
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Extragradient Method with Variance Reduction for Stochastic Variational Inequalities
• Stochastic finance. An introduction in discrete time
• On consistency of stochastic dominance and mean-semideviation models

This page was built for publication: A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization