Data-Driven Evolutionary Algorithm With Perturbation-Based Ensemble Surrogates

Abstract

Data-driven evolutionary algorithms (DDEAs) aim to utilize data and surrogates to drive optimization, which is useful and efficient when the objective function of the optimization problem is expensive or difficult to access. However, the performance of DDEAs relies on their surrogate quality and often deteriorates if the amount of available data decreases. To solve these problems, this article proposes a new DDEA framework with perturbation-based ensemble surrogates (DDEA-PES), which contain two efficient mechanisms. The first is a diverse surrogate generation method that can generate diverse surrogates through performing data perturbations on the available data. The second is a selective ensemble method that selects some of the prebuilt surrogates to form a final ensemble surrogate model. By combining these two mechanisms, the proposed DDEA-PES framework has three advantages, including larger data quantity, better data utilization, and higher surrogate accuracy. To validate the effectiveness of the proposed framework, this article provides both theoretical and experimental analyses. For the experimental comparisons, a specific DDEA-PES algorithm is developed as an instance by adopting a genetic algorithm as the optimizer and radial basis function neural networks as the base models. The experimental results on widely used benchmarks and an aerodynamic airfoil design real-world optimization problem show that the proposed DDEA-PES algorithm outperforms some state-of-the-art DDEAs. Moreover, when compared with traditional nondata-driven methods, the proposed DDEA-PES algorithm only requires about 2% computational budgets to produce competitive results.

Surrogate-Assisted Hybrid-Model Estimation of Distribution Algorithm for Mixed-Variable Hyperparameters Optimization in Convolutional Neural Networks

“…Furthermore, how to evolve the network depth and topology of CNNs is worthy of further research. Also, more efficient optimization paradigms can be considered for CNN optimization in different scenarios, where potential optimization paradigms include data-driven optimization [61], large-scale optimization [62], dynamic optimization [63], many-objective optimization [64], multi-modal optimization [65], expensive optimization [66], and parallel [67] and distributed optimization [68]. In addition, the SHEDA is potential for solving more challenging learning tasks in complex real-world applications, such as healthcare application [69] and autonomous robot application [70], which will be further explored and studied.…”

A survey on evolutionary computation for complex continuous optimization

“…To this aim, very recently, Li et al (2020c) proposed to build an accurate surrogate by efficiently manipulating the small number of available data via a localized data generation (LDG) method, so as to design a boosting DDEA with LDG (BDDEA-LDG). Moreover, Li et al (2020d) further proposed a DDEA with perturbation-based ensemble surrogates (DDEA-PES) on the small number of available data. The few-shot true evaluated data makes the algorithms slighter and easier for using.…”

“…Although the evaluation of airfoil performance requires timeconsuming CFD simulations, the proposed algorithm can obtain a high-quality solution efficiently through active learning-based surrogates. Similarly, Li et al (2020d) applied GA with perturbation-based ensemble surrogates for the expensive airfoil design optimization as well and obtained great results. In an expensive shape optimization of an air intake ventilation system, Chugh et al (2017) proposed a Kriging-based EA to tackle three main challenges, i.e., formulating the optimization problem, connecting different simulation tools, and dealing with computationally expensive objective functions, which obtained promising results in the blast furnace optimization problem.…”

Many-Objective Job-Shop Scheduling: A Multiple Populations for Multiple Objectives-Based Genetic Algorithm Approach

“…To efficiently solve the proposed MaJSSP, the multiple populations for multiple objectives (MPMO) [22] framework that has shown excellent performance on both multiobjective optimization [23], [24] and many-objective optimization [25] is adopted. Evolutionary computation algorithms are promising optimizers for various optimization problems [26]- [29]. In particular, the GA has shown powerful efficiency in solving discrete optimization problems [30], [31].…”