A single cut proximal bundle method for stochastic convex composite optimization
Preprint
Abstract
In this paper, we consider optimization problems where the objective is the sum of a function given by an expectation and a closed convex composite function. For such problems, we propose a stochastic composite proximal bundle (SCPB) method with optimal complexity. The method does not require estimation of parameters involved in the assumptions on the objective functions. Moreover, to the best of our knowledge, this is the first proximal bundle method for stochastic programming able to deal with continuous distributions. Finally, we present computational results showing that SCPB substantially outperforms the robust stochastic approximation method on all instances considered.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Inexact stochastic mirror descent for two-stage nonlinear stochastic programsMathematical Programming, 2020
- Non-asymptotic confidence bounds for the optimal value of a stochastic programOptimization Methods and Software, 2017
- Multistep stochastic mirror descent for risk-averse convex stochastic programs based on extended polyhedral risk measuresMathematical Programming, 2016
- Convergence Analysis of Sampling-Based Decomposition Methods for Risk-Averse Multistage Stochastic Convex ProgramsSIAM Journal on Optimization, 2016
- Robust Stochastic Approximation Approach to Stochastic ProgrammingSIAM Journal on Optimization, 2009
- Primal-dual subgradient methods for convex problemsMathematical Programming, 2007
- The Sample Average Approximation Method Applied to Stochastic Routing Problems: A Computational StudyComputational Optimization and Applications, 2003
- Acceleration of Stochastic Approximation by AveragingSIAM Journal on Control and Optimization, 1992
- Asymptotic analysis of stochastic programsAnnals of Operations Research, 1991
- A multicut algorithm for two-stage stochastic linear programsEuropean Journal of Operational Research, 1988