A Reliability Theory of Compromise Decisions for Large-Scale Stochastic Programs

TL;DR

This paper develops a theoretical framework to evaluate the reliability of compromise decisions in large-scale stochastic programming, focusing on variance reduction and sample complexity bounds.

Contribution

It introduces a reliability theory for compromise decisions, quantifies their reliability using pessimistic distance, and employs Rademacher averages to bound sample complexity.

Findings

Quantifies the expectation and variance of the pessimistic distance.

Provides bounds on sample complexity using Rademacher averages.

Analyzes the reliability of solutions from compromise decision processes.

Abstract

Stochastic programming models can lead to very large-scale optimization problems for which it may be impossible to enumerate all possible scenarios. In such cases, one adopts a sampling-based solution methodology in which case the reliability of the resulting decisions may be suspect. For such instances, it is advisable to adopt methodologies that promote variance reduction. One such approach goes under a framework known as "compromise decision", which requires multiple replications of the solution procedure. This paper studies the reliability of stochastic programming solutions resulting from the "compromise decision" process. This process is characterized by minimizing an aggregation of objective function approximations across replications, presumably conducted in parallel. We refer to the post-parallel-processing problem as the problem of "compromise decision". We quantify the reliability of compromise decisions by estimating the expectation and variance of the "pessimistic distance" of sampled instances from the set of true optimal decisions. Such pessimistic distance is defined as an estimate of the largest possible distance of the solution of the sampled instance from the "true" optimal solution set. The Rademacher average of instances is used to bound the sample complexity of the compromise decision.