Extreme Learning Machines for Variance-Based Global Sensitivity Analysis

• Activity Number: 403 - Research Advances at the Interface of Uncertainty Quantification and Machine Learning for High-Consequence Problems
• Type: Invited
• Date/Time: Wednesday, August 10, 2022 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Defense and National Security
• Author(s): John Darges* and Alen Alexanderian and Pierre Gremaud
• Companies: North Carolina State University and North Carolina State University and North Carolina State University
• Keywords: Extreme learning machine; Global sensitivity analysis; Sobol' indices; Analysis of variance; Regression; Sparsification

Abstract

Variance-based global sensitivity analysis (GSA) can provide a wealth of information when applied to complex models. A well-known Achilles' heel of this approach is its computational cost which often renders it unfeasible in practice. An appealing alternative is to analyze instead the sensitivity of a surrogate model with the goal of lowering computational costs while maintaining sufficient accuracy. Should a surrogate be "simple" enough to be amenable to the analytical calculations of its Sobol' indices, the cost of GSA is essentially reduced to the construction of the surrogate. We propose a new class of sparse weight Extreme Learning Machines (SW-ELMs) which, when considered as surrogates in the context of GSA, admit analytical formulas for their Sobol' indices and, unlike the standard ELMs, yield accurate approximations of these indices. The effectiveness of this approach is illustrated through both traditional benchmarks in the field and on a chemical reaction network.