A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization
From MaRDI portal
Publication:4995000
Abstract: We propose a single time-scale stochastic subgradient method for constrained optimization of a composition of several nonsmooth and nonconvex functions. The functions are assumed to be locally Lipschitz and differentiable in a generalized sense. Only stochastic estimates of the values and generalized derivatives of the functions are used. The method is parameter-free. We prove convergence with probability one of the method, by associating with it a system of differential inclusions and devising a nondifferentiable Lyapunov function for this system. For problems with functions having Lipschitz continuous derivatives, the method finds a point satisfying an optimality measure with error of order , after executing iterations with constant stepsize.
Recommendations
- Stochastic multilevel composition optimization algorithms with level-independent convergence rates
- Multilevel stochastic gradient methods for nested composition optimization
- Multilevel composite stochastic optimization via nested variance reduction
- A hybrid stochastic optimization framework for composite nonconvex optimization
- A stochastic Nesterov's smoothing accelerated method for general nonsmooth constrained stochastic composite convex optimization
- scientific article; zbMATH DE number 3887445
- A multistep stochastic ϵ-subgradient method of minimizing a convex function
- A multilevel proximal gradient algorithm for a class of composite optimization problems
- Stochastic subgradient method for quasi-convex optimization problems
- Subregular recourse in nonlinear multistage stochastic optimization
Cites work
- scientific article; zbMATH DE number 5348356 (Why is no real title available?)
- scientific article; zbMATH DE number 3926637 (Why is no real title available?)
- scientific article; zbMATH DE number 4035561 (Why is no real title available?)
- scientific article; zbMATH DE number 3707685 (Why is no real title available?)
- scientific article; zbMATH DE number 1972910 (Why is no real title available?)
- scientific article; zbMATH DE number 3437904 (Why is no real title available?)
- scientific article; zbMATH DE number 3333703 (Why is no real title available?)
- A Linearization Method for Nonsmooth Stochastic Programming Problems
- A Single Timescale Stochastic Approximation Method for Nested Stochastic Optimization
- Accelerating Stochastic Composition Optimization
- Analysis of recursive stochastic algorithms
- Clarke Subgradients of Stratifiable Functions
- Coherent measures of risk
- Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization
- Curves of descent
- Extragradient Method with Variance Reduction for Stochastic Variational Inequalities
- From stochastic dominance to mean-risk models: Semideviations as risk measures
- Generalized Gradients and Applications
- Generalized gradients of Lipschitz functionals
- Lectures on Stochastic Programming
- Multilevel stochastic gradient methods for nested composition optimization
- On consistency of stochastic dominance and mean-semideviation models
- Regularized Iterative Stochastic Approximation Methods for Stochastic Variational Inequality Problems
- Sample average approximation method for compound stochastic optimization problems
- Semismooth and Semiconvex Functions in Constrained Optimization
- Statistical estimation of composite risk functionals and risk optimization problems
- Stochastic Approximations and Differential Inclusions
- Stochastic Approximations and Differential Inclusions, Part II: Applications
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Stochastic Methods for Composite and Weakly Convex Optimization Problems
- Stochastic approximation methods for constrained and unconstrained systems
- Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
- Stochastic finance. An introduction in discrete time
- Stochastic model-based minimization of weakly convex functions
- Stochastic subgradient method converges on tame functions
Cited in
(20)- Stochastic multilevel composition optimization algorithms with level-independent convergence rates
- scientific article; zbMATH DE number 3887445 (Why is no real title available?)
- Mini-Batch Risk Forms
- Stochastic subgradient algorithm for nonsmooth nonconvex optimization
- Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems
- Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization
- Subgradient Sampling for Nonsmooth Nonconvex Minimization
- Distributed stochastic compositional optimization problems over directed networks
- Multilevel stochastic gradient methods for nested composition optimization
- Proximally guided stochastic subgradient method for nonsmooth, nonconvex problems
- A functional model method for nonconvex nonsmooth conditional stochastic optimization
- Stochastic nested primal-dual method for nonconvex constrained composition optimization
- Zeroth-order Riemannian averaging stochastic approximation algorithms
- An interior stochastic gradient method for a class of non-Lipschitz optimization problems
- A stochastic subgradient method for distributionally robust non-convex and non-smooth learning
- Stochastic composition optimization of functions without Lipschitz continuous gradient
- Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions
- A stochastic successive minimization method for nonsmooth nonconvex optimization with applications to transceiver design in wireless communication networks
- Multilevel composite stochastic optimization via nested variance reduction
- A geometric integration approach to nonsmooth, nonconvex optimisation
This page was built for publication: A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4995000)
