Penalty methods with stochastic approximation for stochastic nonlinear programming
From MaRDI portal
Abstract: In this paper, we propose a class of penalty methods with stochastic approximation for solving stochastic nonlinear programming problems. We assume that only noisy gradients or function values of the objective function are available via calls to a stochastic first-order or zeroth-order oracle. In each iteration of the proposed methods, we minimize an exact penalty function which is nonsmooth and nonconvex with only stochastic first-order or zeroth-order information available. Stochastic approximation algorithms are presented for solving this particular subproblem. The worst-case complexity of calls to the stochastic first-order (or zeroth-order) oracle for the proposed penalty methods for obtaining an -stochastic critical point is analyzed.
Recommendations
- Stochastic penalty function methods for nonsmooth constrained minimization
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Stochastic nonlinear complementarity problems: stochastic programming reformulation and penalty-based approximation method
- scientific article; zbMATH DE number 3887439
- An approximation-exact penalty function method of solving single stage stochastic programming
Cites work
- A method of aggregate stochastic subgradients with on-line stepsize rules for convex stochastic programming problems
- A Stochastic Approximation Method
- Accelerated gradient methods for nonconvex nonlinear and stochastic programming
- Acceleration of Stochastic Approximation by Averaging
- An optimal method for stochastic composite optimization
- Asymptotic Distribution of Stochastic Approximation Procedures
- Conditions for convergence of trust region algorithms for nonsmooth optimization
- Convergence theory for nonconvex stochastic programming with an application to mixed logit
- scientific article; zbMATH DE number 3790208 (Why is no real title available?)
- scientific article; zbMATH DE number 3612778 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Introduction to stochastic programming.
- Learning by mirror averaging
- Lectures on Stochastic Programming
- Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
- New method of stochastic approximation type
- On a Stochastic Approximation Method
- On the evaluation complexity of composite function minimization with applications to nonconvex nonlinear programming
- Online learning for matrix factorization and sparse coding
- Optimal Stochastic Approximation Algorithms for Strongly Convex Stochastic Composite Optimization I: A Generic Algorithmic Framework
- Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization. II: Shrinking procedures and optimal algorithms
- Optimization for simulation: theory vs. practice
- Randomized smoothing for stochastic optimization
- Robust Stochastic Approximation Approach to Stochastic Programming
- Smoothing and worst-case complexity for direct-search methods in nonsmooth optimization
- Stochastic block mirror descent methods for nonsmooth and stochastic optimization
- Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
- Stochastic first-order methods with random constraint projection
- stochastic quasigradient methods and their application to system optimization†
- The sample average approximation method for stochastic discrete optimization
- Validation analysis of mirror descent stochastic approximation method
- Worst-case complexity of smoothing quadratic regularization methods for non-Lipschitzian optimization
Cited in
(24)- Variable sample size method for equality constrained optimization problems
- Stochastic penalty function methods for nonsmooth constrained minimization
- Complexity of an inexact proximal-point penalty method for constrained smooth non-convex optimization
- Exact penalization in stochastic programming -- calmness and constraint qualification
- Stochastic first-order methods for convex and nonconvex functional constrained optimization
- Penalty function with memory for discrete optimization via simulation with stochastic constraints
- Expected Utility, Penalty Functions, and Duality in Stochastic Nonlinear Programming
- Stochastic optimisation with inequality constraints using simultaneous perturbations and penalty functions
- Exact penalty functions in single-stage stochastic programming1
- scientific article; zbMATH DE number 599208 (Why is no real title available?)
- Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
- Stochastic regularized Newton methods for nonlinear equations
- Stochastic inexact augmented Lagrangian method for nonconvex expectation constrained optimization
- Stochastic nested primal-dual method for nonconvex constrained composition optimization
- Stochastic optimization over proximally smooth sets
- Level constrained first order methods for function constrained optimization
- Variance-reduced first-order methods for deterministically constrained stochastic nonconvex optimization with strong convergence guarantees
- Complexity analysis of inexact cubic-regularized primal-dual methods for finding second-order stationary points
- A two-phase stochastic momentum-based algorithm for nonconvex expectation-constrained optimization
- First-order methods for nonsmooth nonconvex functional constrained optimization with or without Slater points
- A SPIDER-type stochastic subgradient method for expectation-constrained nonconvex nonsmooth optimization
- Adaptive-batch stochastic gradient descent for constrained optimization based on relaxed barrier functions
- Robust stochastic gradient descent for linearly constrained problems via adaptive barrier amplification
- Survey on first-order algorithms for solving functional constrained optimization problems
This page was built for publication: Penalty methods with stochastic approximation for stochastic nonlinear programming
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2970100)
