Journal Article10.1109/tevc.2023.3291614
Surrogate-Assisted Evolutionary Algorithm with Model and Infill Criterion Auto-Configuration
15
TL;DR: In this paper , a two-level multi-armed bandit problem (TL-MAB) is proposed to select the surrogate model and infill criterion in an online manner.
read more
Abstract: Surrogate-assisted evolutionary algorithms (SAEAs) have proven to be effective in solving computationally expensive optimization problems (EOPs). However, the performance of SAEAs heavily relies on the surrogate model and infill criterion used. To improve the generalization of SAEAs and enable them to solve a wide range of EOPs, this paper proposes an SAEA called AutoSAEA, which features model and infill criterion auto-configuration. Specifically, AutoSAEA formulates model and infill criterion selection as a two-level multi-armed bandit problem (TL-MAB). The first and second levels cooperate in selecting the surrogate model and infill criterion, respectively. A two-level reward (TL-R) measures the value of the surrogate model and infill criterion, while a two-level upper confidence bound (TL-UCB) selects the model and infill criterion in an online manner. Numerous experiments validate the superiority of AutoSAEA over some state-of-the-art SAEAs on complex benchmark problems and a real-world oil reservoir production optimization problem.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Surrogate-Assisted Differential Evolution with fitness-independent parameter adaptation for high-dimensional expensive optimization
Laiqi Yu,Chongle Ren,Zhenyu Meng +2 more
TL;DR: This paper proposes SADE-FI, a surrogate-assisted Differential Evolution algorithm with fitness-independent parameter adaptation, to tackle high-dimensional expensive optimization problems, outperforming state-of-the-art algorithms on benchmark functions and a real-world antenna array design problem.
6
A multi-strategy surrogate-assisted social learning particle swarm optimization for expensive optimization and applications
Shu‐Chuan Chu,Yuan Xu,Jeng‐Shyang Pan,Bertrand M.T. Lin,Zne‐Jung Lee +4 more
TL;DR: A multi-strategy surrogate-assisted social learning particle swarm optimization (SASLPSO) algorithm is proposed to solve expensive optimization problems. The algorithm combines global surrogate (GS) and adaptive local surrogate (ALS) strategies to balance global exploration and local exploitation. RGBPS strategy is also introduced to screen promising particles for real function evaluation. The SASLPSO algorithm outperforms other comparison algorithms on benchmark functions and real-world problems.
6
Evaluation Model and Algorithm Optimization of Intelligent Manufacturing System on the Basis of BP Neural Network
Wei Tian,Yu Cao +1 more
TL;DR: This study optimizes the Back Propagation (BP) neural network using Firefly Algorithm (FA) and Sparrow Search Algorithm (SSA), achieving a 1.34% and 0.41% average error, significantly outperforming other advanced algorithms in intelligent manufacturing system evaluation.
4
A Kriging-assisted Double Population Differential Evolution for Mixed-Integer Expensive Constrained Optimization Problems with Mixed Constraints
Yuanhao Liu,Zan Yang,Danyang Xu,Haobo Qiu,Liang Gao +4 more
TL;DR: A Kriging-assisted Double Population Differential Evolution (KDPDE) algorithm is proposed to solve mixed-integer Expensive Constrained Optimization Problems (ECOPs) with mixed constraints, balancing convergence and robustness through elite retention and population diversity maintenance.
1
Surrogate-Assisted Search with Competitive Knowledge Transfer for Expensive Optimization
Xiaoming Xue,Yao Hu,Liang Feng,Kai Zhang,Linqi Song,Kay Chen Tan +5 more
- 13 Aug 2024
TL;DR: This paper proposes a plug-and-play competitive knowledge transfer method to boost surrogate-assisted evolutionary algorithms for expensive optimization problems, enabling knowledge competition to elect the winner and boosting search speed, with theoretical convergence gain analysis and experimental verification.
References
Surrogate-Assisted Cooperative Swarm Optimization of High-Dimensional Expensive Problems
TL;DR: Empirical studies demonstrate that the proposed surrogate-assisted cooperative swarm optimization algorithm is able to find high-quality solutions for high-dimensional problems on a limited computational budget.
398
Committee-Based Active Learning for Surrogate-Assisted Particle Swarm Optimization of Expensive Problems
TL;DR: A novel surrogate-assisted particle swarm optimization (PSO) inspired from committee-based active learning (CAL) is proposed and experimental results demonstrate that the proposed algorithm is able to achieve better or competitive solutions with a limited budget of hundreds of exact FEs.
397
A Classification-Based Surrogate-Assisted Evolutionary Algorithm for Expensive Many-Objective Optimization
TL;DR: A surrogate-assisted many-objective evolutionary algorithm that uses an artificial neural network to predict the dominance relationship between candidate solutions and reference solutions instead of approximating the objective values separately is proposed.
361
A statistical method for global optimization
TL;DR: Comparison with published results for several test functions indicates that the procedure is very efficient in finding the global optimum of a multimodal function, and in terminating with relatively few evaluations.
359
An evidence-theoretic k-NN rule with parameter optimization
L.M. Zouhal,Thierry Denoeux +1 more
- 01 May 1998
TL;DR: A learning procedure for optimizing the parameters in the evidence-theoretic k-nearest neighbor rule, a pattern classification method based on the Dempster-Shafer theory of belief functions, is presented.
315