A Parallel Technique for Multi-objective Bayesian Global Optimization: Using a Batch Selection of Probability of Improvement
@article{Yang2022APT, title={A Parallel Technique for Multi-objective Bayesian Global Optimization: Using a Batch Selection of Probability of Improvement}, author={Kaifeng Yang and Guozhi Dong and Michael Affenzeller}, journal={Swarm Evol. Comput.}, year={2022}, volume={75}, pages={101183} }
Bayesian global optimization (BGO) is an efficient surrogate-assisted technique for problems involving expensive evaluations. A parallel technique can be used to parallelly evaluate the true-expensive objective functions in one iteration to boost the execution time. An effective and straightforward approach is to design an acquisition function that can evaluate the performance of a bath of multiple solutions, instead of a single point/solution, in one iteration. This paper proposes five…
Figures and Tables from this paper
References
SHOWING 1-10 OF 66 REFERENCES
A Generator for Multiobjective Test Problems With Difficult-to-Approximate Pareto Front Boundaries
- Computer ScienceIEEE Transactions on Evolutionary Computation
- 2019
It is concluded that the rational allocation of computational resources between different PF parts is crucial for MOEAs to handle the problems with DtA PF boundaries.
A review of statistical models for global optimization
- EngineeringJ. Glob. Optim.
- 1992
Rationality of the search for a global minimum is formulated axiomatically and the features of the corresponding algorithm are derived from the axioms.
Choose Appropriate Subproblems for Collaborative Modeling in Expensive Multiobjective Optimization
- Computer ScienceIEEE Transactions on Cybernetics
- 2023
This article proposes an adaptive subproblem selection (ASS) strategy to identify the most promising subproblems for further modeling, and uses the collaborative multioutput Gaussian process surrogate to model them jointly.
Kriging is well-suited to parallelize optimization
- Computer Science
- 2010
This work investigates a multi-points optimization criterion, the multipoints expected improvement (\(q-{\mathbb E}I\)), aimed at choosing several points at the same time, and proposes two classes of heuristic strategies meant to approximately optimize the Q-EI, and applies them to the classical Branin-Hoo test-case function.
Infill Criteria for Multiobjective Bayesian Optimization
- Computer ScienceHigh-Performance Simulation-Based Optimization
- 2020
This chapter will summarize main properties of these infill criteria, including continuity and differentiability as well as monotonicity properties of the variance and mean value, necessary for constructing global optimization algorithms for non-convex problems.
A benchmark test suite for evolutionary many-objective optimization
- Computer Science
- 2017
This paper carefully select (or modify) 15 test problems with diverse properties to construct a benchmark test suite, aiming to promote the research of evolutionary many-objective optimization (EMaO) via suggesting a set of testblems with a good representation of various real-world scenarios.
Interactive exploration of design trade-offs
- Computer Science, EconomicsACM Trans. Graph.
- 2018
This work proposes a novel approach to discover the Pareto front, allowing designers to navigate the landscape of compromises efficiently, and allows the entire trade-off manifold as a small collection of patches that comprise a high-quality and piecewise-smooth approximation.
Efficient computation of expected hypervolume improvement using box decomposition algorithms
- Computer ScienceJournal of Global Optimization
- 2019
This paper proposes an efficient algorithm for the exact calculation of the EHVI for in a generic case based on partitioning the integration volume into a set of axis-parallel slices and utilizing a new hyperbox decomposition technique, which is proposed by Dächert et al.
A data augmentation based Kriging-assisted reference vector guided evolutionary algorithm for expensive dynamic multi-objective optimization
- Computer ScienceSwarm Evol. Comput.
- 2022
A surrogate-assisted evolutionary algorithm for expensive many-objective optimization in the refining process
- Computer ScienceSwarm Evol. Comput.
- 2022