Improved sampling strategies for ensemble-based optimization

Improved sampling strategies for ensemble-based optimization

Ramaswamy, K.R.
Fonseca, R.M.
Leeuwenburgh, O.
Siraj, M.M.
van den Hof, P.M.J.

2020

We are concerned with the efficiency of stochastic gradient estimation methods for large-scale nonlinear optimization in the presence of uncertainty. These methods aim to estimate an approximate gradient from a limited number of random input vector samples and corresponding objective function values. Ensemble methods usually employ Gaussian sampling to generate the input samples. It is known from the optimal design theory that the quality of sample-based approximations is affected by the distribution of the samples. We therefore evaluate six different sampling strategies to optimization of a high-dimensional analytical benchmark optimization problem, and, in a second example, to optimization of oil reservoir management strategies with and without geological uncertainty. The effectiveness of the sampling strategies is analyzed based on the quality of the estimated gradient, the final objective function value, the rate of the convergence, and the robustness of the gradient estimate. Based on the results, an improved version of the stochastic simplex approximate gradient method is proposed based on UE(s2) sampling designs for supersaturated cases that outperforms all alternative approaches. We additionally introduce two new strategies that outperform the UE(s2) designs previously suggested in the literature. © 2019, The Author(s).

Robust optimization
Ensemble methods
Approximate gradient
Sampling strategies
Geological Survey Netherlands
2015 Energy

http://resolver.tudelft.nl/uuid:2d9ba0ee-1cd8-415f-a5c0-830cb1a9d9bc

https://doi.org/10.1007/s10596-019-09914-8

876314

Springer

1420-0597

Computational Geosciences, 1-13

article