The robust binomial approach to chance-constrained optimization problems with application to stochastic partitioning of large process networks

In this paper, we study an interpretation of the sample-based approach to chance-constrained programming problems grounded in statistical testing theory. On top of being simple and pragmatic, this approach is theoretically well founded, non parametric and leads to a general method for leveraging existing heuristic algorithms for the deterministic case to their chance-constrained counterparts. Throughout this paper, this algorithm design approach is illustrated on a real world graph partitioning problem which crops up in the field of compilation for parallel systems. Extensive computational results illustrate the practical relevance of the approach, as well as the robustness of the obtained solutions.