Global sensitivity analysis for optimization with variable selection

TL;DR

This paper introduces a new sensitivity analysis method based on the Hilbert-Schmidt Independence Criterion to identify influential variables in optimization problems, enabling effective variable reduction and fewer function evaluations.

Contribution

It proposes a novel influence measure tailored for optimization, improving variable selection and reducing computational costs compared to traditional regression-based methods.

Findings

The new sensitivity measure effectively identifies key variables.

Greedy variable setting strategies reduce function evaluations.

Applications show maintained solution quality with fewer evaluations.

Abstract

The optimization of high dimensional functions is a key issue in engineering problems but it frequently comes at a cost that is not acceptable since it usually involves a complex and expensive computer code. Engineers often overcome this limitation by first identifying which parameters drive the most the function variations: non-influential variables are set to a fixed value and the optimization procedure is carried out with the remaining influential variables. Such variable selection is performed through influence measures that are meaningful for regression problems. However it does not account for the specific structure of optimization problems where we would like to identify which variables most lead to constraints satisfaction and low values of the objective function. In this paper, we propose a new sensitivity analysis that accounts for the specific aspects of optimization problems. In particular, we introduce an influence measure based on the Hilbert-Schmidt Independence Criterion to characterize whether a design variable matters to reach low values of the objective function and to satisfy the constraints. This sensitivity measure makes it possible to sort the inputs and reduce the problem dimension. We compare a random and a greedy strategies to set the values of the non-influential variables before conducting a local optimization. Applications to several test-cases show that this variable selection and the greedy strategy significantly reduce the number of function evaluations at a limited cost in terms of solution performance.