Skip to yearly menu bar Skip to main content


Poster
in
Workshop: NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences

Multi-fidelity Constrained Optimization for Stochastic Black Box Simulators

Kislaya Ravi · Atul Agrawal · Phaedon S Koutsourelakis · Hans-Joachim Bungartz


Abstract:

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.

Chat is not available.