Bing Wang
ABSTRACT
For several real-world optimization problems, the evaluation of response functions may be expensive, computationally or otherwise. The number of design evaluations one can afford for such problems are therefore severely limited. Surrogate models are commonly used to guide the search for such computationally expensive optimization problems (CEOP). The surrogate models built using a limited number of true evaluations are used to identify the next infill/sampling location. Expected improvement (EI) is a well known infill criteria which balances exploration and exploitation by accounting for both mean and uncertainties in the current model. However, recent studies have shown that, somewhat counter-intuitively, a greedy ("believer") strategy can compete well with EI in solving CEOPs. In this study, we are interested in examining the relative performance of the two infill methods across a range of problems, and identify the influencing factors affecting their performance. Based on the empirical analysis, we further propose an algorithm incorporating the strengths of the two strategies. The numerical experiments demonstrate that the proposed algorithm is able to achieve a competitive performance across a range of problems with diverse characteristics; making it a strong candidate for solving black-box CEOPs.
- K. Deb and A. Sinha. 2009. Constructing test problems for bilevel evolutionary multi-objective optimization. In IEEE Congress on Evolutionary Computation. 1153--1160.Google Scholar
- Jerome H Friedman and Nicholas I Fisher. 1999. Bump hunting in high-dimensional data. Statistics and Computing 9, 2 (1999), 123--143.Google ScholarDigital Library
- Ingo Paenke, Jurgen Branke, and Yaochu Jin. 2006. Efficient Search for Robust Solutions by Means of Evolutionary Algorithms and Fitness Approximation. IEEE transactions on evolutionary computation 10, 4 (2006), 405--420.Google ScholarDigital Library
- Frederik Rehbach, Martin Zaefferer, Boris Naujoks, and Thomas Bartz-Beielstein. 2020. Expected Improvement versus Predicted Value in Surrogate-Based Optimization. In Genetic and Evolutionary Computation Conference (GECCO).Google ScholarDigital Library
- Ankur Sinha, Pekka Malo, and Kalyanmoy Deb. 2014. Test problem construction for single-objective bilevel optimization. Evolutionary computation 22, 3 (2014), 439--477.Google Scholar
- Sonja Surjanovic and Derek Bingham. 2013. Virtual Library of Simulation Experiments: Test Functions and Datasets. Retrieved January 11, 2021, from http://www.sfu.ca/~ssurjano (2013).Google Scholar
- Bridging kriging believer and expected improvement using bump hunting for expensive black-box optimization
Recommendations
Comparing Expected Improvement and Kriging Believer for Expensive Bilevel Optimization
2021 IEEE Congress on Evolutionary Computation (CEC)Bilevel optimization refers to a specialized class of problems where one optimization task is nested as a constraint within another. Such problems emerge in a range of real-world scenarios involving hierarchical decision-making, and significant literature ...
Expected improvement for expensive optimization: a review
AbstractThe expected improvement (EI) algorithm is a very popular method for expensive optimization problems. In the past twenty years, the EI criterion has been extended to deal with a wide range of expensive optimization problems. This paper gives a ...
An efficient multi-objective PSO algorithm assisted by Kriging metamodel for expensive black-box problems
The huge computational overhead is the main challenge in the application of community based optimization methods, such as multi-objective particle swarm optimization and multi-objective genetic algorithm, to deal with the multi-objective optimization ...
Comments