Adaptive scenario subset selection for min-max black-box continuous optimization

We handle min-max black-box optimization problems in which the scenario variable to be maximized is discrete and the design variable to be minimized is a continuous vector. To reduce the number of objective function calls, which are assumed to be computationally expensive, we propose an approach that samples a subset of scenarios at each iteration to approximate the worst-case objective function and apply the covariance matrix adaptation evolution strategy to the approximated worst-case objective function. In addition, we develop an adaptation mechanism for the probability of sampling each scenario. Moreover, we introduce the notion of support scenarios to characterize min-max optimization problems with discrete scenario variables and design test problems with various characteristics of support scenarios. Empirical evaluations reveal that the proposed approach learns to sample the set of support scenarios, being more efficient than sampling all the scenarios, especially when the available scenarios outnumber the support scenarios.

[1]  Youhei Akimoto,et al.  Well placement optimization under geological statistical uncertainty , 2019, GECCO.

[2]  Youhei Akimoto,et al.  Diagonal Acceleration for Covariance Matrix Adaptation Evolution Strategies , 2019, Evolutionary Computation.

[3]  Youhei Akimoto,et al.  Parallel Workflow to Optimize Well Placement in Heterogeneous Reservoir using Covariance Matrix Adaptation Evolution Strategy , 2019, SSRN Electronic Journal.

[4]  Kay Chen Tan,et al.  A New Differential Evolution Algorithm for Minimax Optimization in Robust Design , 2018, IEEE Transactions on Cybernetics.

[5]  Thomas Bartz-Beielstein,et al.  Model-based methods for continuous and discrete global optimization , 2017, Appl. Soft Comput..

[6]  Handing Wang,et al.  Data-Driven Surrogate-Assisted Multiobjective Evolutionary Optimization of a Trauma System , 2016, IEEE Transactions on Evolutionary Computation.

[7]  Zukui Li,et al.  Reservoir Geological Uncertainty Reduction: an Optimization-Based Method Using Multiple Static Measures , 2015, Mathematical Geosciences.

[8]  Zukui Li,et al.  Optimal scenario reduction framework based on distance of uncertainty distribution and output performance: I. Single reduction via mixed integer linear optimization , 2014, Comput. Chem. Eng..

[9]  Anne Auger,et al.  Principled Design of Continuous Stochastic Search: From Theory to Practice , 2014, Theory and Principled Methods for the Design of Metaheuristics.

[10]  Anne Auger,et al.  Well Placement Optimization under Uncertainty with CMA-ES Using the Neighborhood , 2012, ArXiv.

[11]  Kengo Nakajima,et al.  Numerical Simulation of Long-Term Fate of CO2 Stored in Deep Reservoir Rocks on Massively Parallel Vector Supercomputer , 2012, VECPAR.

[12]  Stein Krogstad,et al.  Open-source MATLAB implementation of consistent discretisations on complex grids , 2012, Computational Geosciences.

[13]  Akhil Datta-Gupta,et al.  Optimizing smart well controls under geologic uncertainty , 2010 .

[14]  Qingfu Zhang,et al.  A surrogate-assisted evolutionary algorithm for minimax optimization , 2010, IEEE Congress on Evolutionary Computation.

[15]  Jef Caers,et al.  Bootstrap confidence intervals for reservoir model selection techniques , 2010 .

[16]  Jef Caers,et al.  Uncertainty Quantification in Reservoir Performance Using Distances and Kernel Methods--Application to a West Africa Deepwater Turbidite Reservoir , 2009 .

[17]  Alireza Nouri,et al.  Criteria for Ranking Realizations in the Investigation of SAGD Reservoir Performance , 2009 .

[18]  Jef Caers,et al.  Representing Spatial Uncertainty Using Distances and Kernels , 2009 .

[19]  Jürgen Branke,et al.  New Approaches to Coevolutionary Worst-Case Optimization , 2008, PPSN.

[20]  L. Durlofsky,et al.  Optimization of nonconventional wells under uncertainty using statistical proxies , 2006 .

[21]  Leandro dos Santos Coelho,et al.  Co-evolutionary particle swarm optimization for min-max problems using Gaussian distribution , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[22]  Louis J. Durlofsky,et al.  Optimization of Advanced Well Type and Performance , 2004 .

[23]  Yuhui Shi,et al.  Co-evolutionary particle swarm optimization to solve min-max problems , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[24]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

[25]  Mikkel T. Jensen,et al.  A new look at solving minimax problems with coevolutionary genetic algorithms , 2004 .

[26]  Min-Jea Tahk,et al.  Coevolutionary augmented Lagrangian methods for constrained optimization , 2000, IEEE Trans. Evol. Comput..

[27]  H. Barbosa.  A coevolutionary genetic algorithm for constrained optimization , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[28]  Jeffrey W. Herrmann,et al.  A genetic algorithm for minimax optimization problems , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[29]  K. Aziz,et al.  Prediction Of Uncertainty In Reservoir Performance Forecast , 1992 .