Improving Local Convergence in Particle Swarms by Fitness Approximation Using Regression

Bird, Stefan; Li, Xiaodong

doi:10.1007/978-3-642-10701-6_11

Cited by 11 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This defines the margin of separation, the width of which is given by . In order to simplify the optimization problem without changing the solution, SVM will be used to minimize (7) subject to (8) In Eq. (7), the parameter " " is introduced for mathematical convenience only.…”

Section: B Support Vector Machinementioning

confidence: 99%

“…Margarita and Coello [6] proposed to incorporate the concept of fitness inheritance into a multi-objective particle swarm optimization in order to reduce the fitness evaluations. Bird and Li [7] proposed a fitness approximation technique using a least-square regression to find the expected location of the peak and improve the local convergence speed. Parno et al [8] incorporated surrogates constructed using Design and Analysis of Computer Experiments (DACE) as a stand-in for the expensive objective function within the PSO framework.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A constraint approximation assisted PSO for computationally expensive constrained problems

Gao

Sun

Zeng

et al. 2014

Proceeding of the 11th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

Particle swarm optimization (PSO) has been modified to be widely applied in the practical engineering constrained problems. However, with the increment of the complexity of the engineering problems, the fitness and constraint evaluations often cost a lot of time. Many surrogate models assisted PSO algorithms have been proposed for unconstrained problems, however, rarely attention has been paid on the constraint computationally expensive problems. In this paper, the support vector machine (SVM) classifier is proposed to approximate whether a particle is in the feasible region or not so as to save the numbers of constraint violations judgment and improve the efficiency of PSO for solving constrained optimization problems. On-line training technology is used to train a SVM model. The experimental results on 13 benchmark problems show the efficiency of our proposed algorithm.

show abstract

Section: B Support Vector Machinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A constraint approximation assisted PSO for computationally expensive constrained problems

Gao

Sun

Zeng

et al. 2014

Proceeding of the 11th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

show abstract

“…Attempts have also been made to hybridize niching methods with local search procedures, in order to enhance convergence to multiple optima, or in other words, distributed convergence. For example, regression was incorporated into Speciationbased PSO (i.e., rSPSO) for improving local convergence on both static and dynamic multi-modal landscapes in [69]. The faster and more accurate local convergence is achieved by using regression computed based on only a handful of existing individuals in the population.…”

Section: Hybrid Methodsmentioning

confidence: 99%

“…A simple regression method with Speciation-based PSO (so called rSPSO) [69], [120] shows significantly better performance than several other multi-population methods such as mQSO [42]. The regression method can be substituted by other surrogate models such as Kriging [121].…”

Section: B Dynamic Optimizationmentioning

confidence: 99%

Seeking Multiple Solutions: An Updated Survey on Niching Methods and Their Applications

Epitropakis

Deb

et al. 2017

IEEE Trans. Evol. Computat.

Self Cite

264

101

View full text Add to dashboard Cite

Abstract-Multi-modal optimization (MMO) aiming to locate multiple optimal (or near-optimal) solutions in a single simulation is an important topic which has practical relevance in problem solving across many fields. Population-based meta-heuristics have been shown particularly effective in solving MMO prolems, if equipped with specifically-designed diversity-preserving mechanisms, commonly known as niching methods. This paper provides an updated survey on niching methods. The paper first revisits the fundamental concepts about niching and its most representative schemes, then reviews the more recent development of niching methods, including novel and hybrid methods, performance measures, and benchmarks for their assessment. Furthermore, the paper surveys previous attempts on leveraging the capabilities of niching to facilitate various optimization (e.g., multi-objective and dynamic optimization) and machine learning (e.g., clustering, feature selection, and learning ensembles) tasks. A list of successful applications of niching methods to real-world problems is provided to demonstrate that niching methods are able to provide solutions that are difficult for conventional optimization methods to offer. The significant practical value of niching methods is clearly exemplified through these applications. Finally, the paper poses challenges and research questions on niching that are yet to be appropriately addressed. Providing answers to these questions is crucial before we can bring more fruitful benefits of niching to real-world problem solving.

show abstract

“…Parno et al [26] used a Kriging surrogate to improve the efficiency of PSO for simulation-based problems and applied it to a 6-D groundwater management problem. Bird and Li [27] incorporated a regression model into PSO algorithm in order to improve local convergence. Tang et al [28] used a hybrid global surrogate model consisting of a quadratic polynomial and an RBF model to develop a surrogate-based PSO method, which was applied to lowdimensional test problems and engineering design problems.…”

Section: Introductionmentioning

confidence: 99%

A two-layer surrogate-assisted particle swarm optimization algorithm

et al. 2014

View full text Add to dashboard Cite

Like most Evolutionary Algorithms (EAs), Particle Swarm Optimization (PSO) usually requires a large number of fitness evaluations to obtain a sufficiently good solution. This poses an obstacle for applying PSO to computationally expensive problems. This paper proposes a two-layer surrogateassisted PSO (TLSAPSO) algorithm, in which a global and a number of local surrogate models are employed for fitness approximation. The global surrogate model aims to smooth out the local optima of the original multimodal fitness function and guide the swarm to fly quickly to an optimum. In the meantime, a local surrogate model constructed using the data samples near the particle is built to achieve a fitness estimation as accurate as possible. The contribution of each surrogate in the search is empirically verified by experiments on uni-and multi-modal problems. The performance of the proposed TLSAPSO algorithm is examined on ten widely used benchmark problems, and the experimental results show that the proposed algorithm is effective and highly competitive with the state-of-the-art, especially for multimodal optimization problems.

show abstract

Improving Local Convergence in Particle Swarms by Fitness Approximation Using Regression

Cited by 11 publications

References 33 publications

A constraint approximation assisted PSO for computationally expensive constrained problems

A constraint approximation assisted PSO for computationally expensive constrained problems

Seeking Multiple Solutions: An Updated Survey on Niching Methods and Their Applications

A two-layer surrogate-assisted particle swarm optimization algorithm

Contact Info

Product

Resources

About