Multi-fidelity Constrained Optimization for Stochastic Black Box Simulators
This addresses a practical issue for engineers and researchers using legacy simulators in design processes, but it appears incremental as it builds on existing optimization methods with specific enhancements.
The paper tackles the problem of constrained optimization for stochastic, expensive, high-dimensional black-box simulators where gradients are unavailable, by introducing the Scout-Nd algorithm that estimates gradients, reduces noise, and uses multi-fidelity schemes to cut computational effort, showing better performance on benchmarks.
Constrained optimization of the parameters of a simulator plays a crucial role in a design process. These problems become challenging when the simulator is stochastic, computationally expensive, and the parameter space is high-dimensional. One can efficiently perform optimization only by utilizing the gradient with respect to the parameters, but these gradients are unavailable in many legacy, black-box codes. We introduce the algorithm Scout-Nd (Stochastic Constrained Optimization for N dimensions) to tackle the issues mentioned earlier by efficiently estimating the gradient, reducing the noise of the gradient estimator, and applying multi-fidelity schemes to further reduce computational effort. We validate our approach on standard benchmarks, demonstrating its effectiveness in optimizing parameters highlighting better performance compared to existing methods.