Validation analysis of mirror descent stochastic approximation method
From MaRDI portal
A basic difficulty for solving stochastic programming problems is that the objective function is given implicitly as the expectation and as such is difficult to compute with high accuracy. A way of solving such problems is to use randomized algorithms based on Monte Carlo sampling. There are two competing approaches of this type: the sampling average approximation (SAA) and the stochastic approximation (SA) methods. An important property of the SAA approach is that it can provide an estimate of the accuracy of an obtained solution by computing upper and lower (confidence) bounds for the optimal value of the true problem. The main goal of the paper is to show that, for a certain class of stochastic convex problems, the mirror descent SA method can also provide similar bounds but with considerably less computational effort.
Recommendations
- On the convergence of mirror descent beyond stochastic convex programming
- Stochastic mirror descent dynamics and their convergence in monotone variational inequalities
- Stochastic block mirror descent methods for nonsmooth and stochastic optimization
- Algorithms of robust stochastic optimization based on mirror descent method
- Algorithms of inertial mirror descent in stochastic convex optimization problems
- Algorithms of inertial mirror descent in convex problems of stochastic optimization
- Ergodic mirror descent
- Variance reduction on general adaptive stochastic mirror descent
- Stochastic mirror descent method for linear ill-posed problems in Banach spaces
- On stochastic mirror descent with interacting particles: convergence properties and variance reduction
Cites work
- A branch and bound method for stochastic global optimization
- A Stochastic Approximation Method
- Acceleration of Stochastic Approximation by Averaging
- scientific article; zbMATH DE number 3296905 (Why is no real title available?)
- Monte Carlo bounding techniques for determinig solution quality in stochastic programs
- New variants of bundle methods
- On complexity of stochastic programming problems
- Robust Stochastic Approximation Approach to Stochastic Programming
- The empirical behavior of sampling methods for stochastic programming
- The sample average approximation method applied to stochastic routing problems: a computational study
- The sample average approximation method for stochastic discrete optimization
Cited in
(52)- Stochastic accelerated alternating direction method of multipliers with importance sampling
- Accelerated schemes for a class of variational inequalities
- Inexact SA method for constrained stochastic convex SDP and application in Chinese stock market
- Generalized conditioning based approaches to computing confidence intervals for solutions to stochastic variational inequalities
- An optimal randomized incremental gradient method
- Dynamic stochastic approximation for multi-stage stochastic optimization
- Inexact stochastic mirror descent for two-stage nonlinear stochastic programs
- On Monte-Carlo methods in convex stochastic optimization
- A stochastic Nesterov's smoothing accelerated method for general nonsmooth constrained stochastic composite convex optimization
- Complexity of stochastic dual dynamic programming
- A primal-dual algorithm for risk minimization
- Algorithms for stochastic optimization with function or expectation constraints
- A heuristic adaptive fast gradient method in stochastic optimization problems
- Variance reduction for sequential sampling in stochastic programming
- Communication-efficient algorithms for decentralized and stochastic optimization
- Asymptotic behaviors of semidefinite programming with a covariance perturbation
- On the efficiency of a randomized mirror descent algorithm in online optimization problems
- A probability metrics approach for reducing the bias of optimality gap estimators in two-stage stochastic linear programming
- Bundle-level type methods uniformly optimal for smooth and nonsmooth convex optimization
- Variance reduction in Monte Carlo sampling-based optimality gap estimators for two-stage stochastic linear programming
- Stochastic block mirror descent methods for nonsmooth and stochastic optimization
- Penalty methods with stochastic approximation for stochastic nonlinear programming
- Simulation-Based Optimality Tests for Stochastic Programs
- Gradient sliding for composite optimization
- On the strong concavity of the dual function of an optimization problem
- Robust Stochastic Approximation Approach to Stochastic Programming
- Level bundle methods for constrained convex optimization with various oracles
- Multilevel stochastic gradient methods for nested composition optimization
- A central limit theorem and hypotheses testing for risk-averse stochastic programs
- Statistics of robust optimization: a generalized empirical likelihood approach
- A data efficient and feasible level set method for stochastic convex optimization with expectation constraints
- Stochastic optimization for dynamic pricing
- Accelerate stochastic subgradient method by leveraging local growth condition
- Multistep stochastic mirror descent for risk-averse convex stochastic programs based on extended polyhedral risk measures
- Analysis of Online Composite Mirror Descent Algorithm
- Stochastic Quasi-Newton Methods for Nonconvex Stochastic Optimization
- On the convergence of mirror descent beyond stochastic convex programming
- Mini-batch stochastic approximation methods for nonconvex stochastic composite optimization
- Faster randomized block sparse Kaczmarz by averaging
- Sample Size Estimates for Risk-Neutral Semilinear PDE-Constrained Optimization
- Momentum-based accelerated mirror descent stochastic approximation for robust topology optimization under stochastic loads
- Consistency of sample-based stationary points for infinite-dimensional stochastic optimization
- Stochastic dual coordinate descent with adaptive heavy ball momentum for linearly constrained convex optimization
- Sequential sample average majorization-minimization
- A model-free first-order method for linear quadratic regulator with \(\tilde{O}(1/\varepsilon)\) sampling complexity
- CV@R-penalised portfolio optimisation with biased stochastic mirror descent
- Randomized quasi-Monte Carlo methods for risk-averse stochastic optimization
- Risk-adaptive approaches to stochastic optimization: a survey
- Introduction to convex optimization in financial markets
- Stochastic intermediate gradient method for convex problems with stochastic inexact oracle
- An inexact primal-dual algorithm for semi-infinite programming
- The CoMirror algorithm with random constraint sampling for convex semi-infinite programming
This page was built for publication: Validation analysis of mirror descent stochastic approximation method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q715058)
