Bayesian optimization of variable-size design space problems
From MaRDI portal
Abstract: Within the framework of complex system design, it is often necessary to solve mixed variable optimization problems, in which the objective and constraint functions can depend simultaneously on continuous and discrete variables. Additionally, complex system design problems occasionally present a variable-size design space. This results in an optimization problem for which the search space varies dynamically (with respect to both number and type of variables) along the optimization process as a function of the values of specific discrete decision variables. Similarly, the number and type of constraints can vary as well. In this paper, two alternative Bayesian Optimization-based approaches are proposed in order to solve this type of optimization problems. The first one consists in a budget allocation strategy allowing to focus the computational budget on the most promising design sub-spaces. The second approach, instead, is based on the definition of a kernel function allowing to compute the covariance between samples characterized by partially different sets of variables. The results obtained on analytical and engineering related test-cases show a faster and more consistent convergence of both proposed methods with respect to the standard approaches.
Recommendations
- Efficient global optimization of constrained mixed variable problems
- Survey on Bayesian optimization methodology and applications
- A Bayesian approach to constrained single- and multi-objective optimization
- Swarm intelligence for mixed-variable design optimization
- Variational Bayesian strategies for high-dimensional, stochastic design problems
Cites work
- A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code
- A Limited Memory Algorithm for Bound Constrained Optimization
- A Simplex Method for Function Minimization
- An Algorithm Model for Mixed Variable Programming
- An automatic method for solving discrete programming problems
- Analysis of multi-objective Kriging-based methods for constrained global optimization
- Application of Bayesian approach to numerical methods of global and stochastic optimization
- Efficient global optimization of expensive black-box functions
- Filter pattern search algorithms for mixed variable constrained optimization problems
- Gaussian processes for machine learning.
- GPflow: a Gaussian process library using TensorFlow
- Group kernels for Gaussian process metamodels with categorical inputs
- Hidden genes genetic optimization for variable-size design space problems
- scientific article; zbMATH DE number 194544 (Why is no real title available?)
- Kernels for vector-valued functions: a review
- Mesh adaptive direct search algorithms for mixed variable optimization
- Metamodels for computer-based engineering design: Survey and recommendations
- Metamodels for mixed variables based on moving least squares. Application to the structural analysis of a rigid frame
- Pattern search algorithms for mixed variable programming
- Sparse on-line Gaussian processes
- Support Vector Machines
- The design and analysis of computer experiments.
- Theory of Reproducing Kernels
Cited in
(10)- Efficient global optimization of constrained mixed variable problems
- A general mathematical framework for constrained mixed-variable blackbox optimization problems with meta and categorical variables
- Multiobjective Tree-Structured Parzen Estimator
- Methods for constrained optimization of expensive mixed-integer multi-objective problems, with application to an internal combustion engine design problem
- Gaussian Process Regression on Nested Spaces
- Fully Bayesian Inference for Latent Variable Gaussian Process Models
- Latent variable Gaussian process models: a rank-based analysis and an alternative approach
- System architecture optimization strategies: dealing with expensive hierarchical problems
- Bayesian quality-diversity optimization for conditional search-space problems
- Variational Bayesian strategies for high-dimensional, stochastic design problems
This page was built for publication: Bayesian optimization of variable-size design space problems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2245699)
