A Robust Scientific Machine Learning for Optimization: A Novel Robustness Theorem

09/13/2022
by   Luana P. Queiroz, et al.
63

Scientific machine learning (SciML) is a field of increasing interest in several different application fields. In an optimization context, SciML-based tools have enabled the development of more efficient optimization methods. However, implementing SciML tools for optimization must be rigorously evaluated and performed with caution. This work proposes the deductions of a robustness test that guarantees the robustness of multiobjective SciML-based optimization by showing that its results respect the universal approximator theorem. The test is applied in the framework of a novel methodology which is evaluated in a series of benchmarks illustrating its consistency. Moreover, the proposed methodology results are compared with feasible regions of rigorous optimization, which requires a significantly higher computational effort. Hence, this work provides a robustness test for guaranteed robustness in applying SciML tools in multiobjective optimization with lower computational effort than the existent alternative.

READ FULL TEXT

page 7

page 9

page 17

page 19

page 24

page 29

page 33

06/17/2019

A Survey of Optimization Methods from a Machine Learning Perspective

Machine learning develops rapidly, which has made many theoretical break...
09/05/2022

A Robust Learning Methodology for Uncertainty-aware Scientific Machine Learning models

Robust learning is an important issue in Scientific Machine Learning (Sc...
04/22/2019

Optimization + Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness

In recent years, the notion of local robustness (or robustness for short...
04/22/2019

Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness

In recent years, the notion of local robustness (or robustness for short...
03/22/2022

Methodology for development of scientific software and test frameworks in function of precision of the expected results

This dissertation focuses on the development process of scientific softw...
06/25/2020

The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approaches

Deep neural networks (DNNs) have become the de facto learning mechanism ...
01/23/2022

Increasing the Cost of Model Extraction with Calibrated Proof of Work

In model extraction attacks, adversaries can steal a machine learning mo...