As potent approaches for addressing computationally expensive optimization problems, surrogate-assisted evolutionary algorithms (SAEAs) have garnered increasing attention. Prevailing endeavors in evolutionary computat...
详细信息
As potent approaches for addressing computationally expensive optimization problems, surrogate-assisted evolutionary algorithms (SAEAs) have garnered increasing attention. Prevailing endeavors in evolutionary computation predominantly concentrate on expensive continuous optimization problems, with a notable scarcity of investigations directed toward expensive combinatorial optimization problems (ECOPs). Nevertheless, numerous ECOPs persist in practical applications. The widespread prevalence of such problems starkly contrasts the limited development of relevant research. Motivated by this disparity, this paper conducts a comprehensive survey on SAEAs tailored to address ECOPs. This survey comprises two primary segments. The first segment synthesizes prevalent global, local, hybrid, and learning search strategies, elucidating their respective strengths and weaknesses. Subsequently, the second segment furnishes an overview of surrogate-based evaluation technologies, delving into three pivotal facets: model selection, construction, and management. The paper also discusses several potential future directions for SAEAs with a focus towards expensive combinatorial optimization.
For many real-world multi-objective optimisation problems, function evaluations are computationally expensive, resulting in a limited budget of function evaluations that can be performed in practice. To tackle such ex...
详细信息
ISBN:
(纸本)9783031700675;9783031700682
For many real-world multi-objective optimisation problems, function evaluations are computationally expensive, resulting in a limited budget of function evaluations that can be performed in practice. To tackle such expensive problems, multi-objective surrogate-assisted evolutionary algorithms (SAEAs) have been introduced. Often, the performance of these EAs is measured after a fixed number of function evaluations (typically several hundreds) and complex surrogate models are found to be the best to use. However, when selecting an SAEA for a real-world problem, the surrogate building time, surrogate evaluation time, function evaluation time, and available optimisation time budget should be considered simultaneously. To gain insight into the performance of various surrogate models under different conditions, we evaluate an EA with and without four surrogate models (both complex and simple) for a range of optimisation time budgets and function evaluation times while considering the surrogate building and surrogate evaluation times. We use 55 BBOB-BIOBJ benchmark problems as well as a real-world problem where the fitness function involves a biomechanical simulation. Our results, on both types of problems, indicate that a larger hypervolume can be obtained with SAEAs when a function evaluation takes longer than 0.384 s (on the hardware we used). While we confirm that state-of-the-art complex surrogate models are mostly the best choice if up to several hundred function evaluations can be performed, we also observe that simple surrogate models can still outperform non-surrogate-assisted EAs if several thousand function evaluations can be performed.
Expensive optimization problems (EOPs) are becoming more and more ubiquitous nowadays. To effectively solve such problems, surrogate-assisted evolutionary algorithms (SAEAs) have been developed. Specifically, a SAEA u...
详细信息
Antenna synthesis is becoming increasingly challenging with tight requirements for C-SWAP (cost, size, weight and power) reduction while maintaining stringent electromagnetic performance specifications. While machine ...
详细信息
Antenna synthesis is becoming increasingly challenging with tight requirements for C-SWAP (cost, size, weight and power) reduction while maintaining stringent electromagnetic performance specifications. While machine learning approaches are increasingly being explored for antenna synthesis, they are still not capable of handling large shape sets with diverse responses. We propose a branched deep convolutional neural network architecture that can serve as a drop-in replacement for a full-wave simulator (it can predict the full spectral response of reflection co-efficient, input impedance and radiation pattern). We show the utility of such models in surrogate-assistedevolutionary optimization for antenna synthesis with arbitrary specification of targeted response. Specifically, we consider the large shape set defined by the set of 16-vertexes polygonal patch antennas and consider antenna synthesis by specifying independent constraints on return loss, radiation pattern and gain. In contrast to online surrogates, our approach is an offline surrogate that is objective-agnostic;trained once, it can be used over multiple optimizations whereby the model training costs become amortized across multiple synthesis requests. Our approach outperforms evolutionary optimizations relying on full-wave solver-based fitness estimation. Specifically, we report the design, fabrication and experimental characterization of three polygon-shaped patch antennas, each fulfilling different objectives (narrow band, dual-band & wide-band). The reported methodology enables rapid synthesis (in seconds), produces verifiable sound designs and is promising for furthering data-driven design methodologies for electromagnetic wave device synthesis.
Expensive Optimization Problems (EOPs) area pressing challenge in real-world applications because they require high-quality solutions under tight computational budgets. To tackle this, numerous surrogate-assisted Evol...
详细信息
Expensive Optimization Problems (EOPs) area pressing challenge in real-world applications because they require high-quality solutions under tight computational budgets. To tackle this, numerous surrogate-assisted evolutionary algorithms (SAEAs) have been proposed that combine evolutionaryalgorithms (EAs) with surrogate models. Recently, researchers have conducted systematic surveys on SAEAs to better showcase their potential in solving EOPs. However, most of these efforts have focused on surrogate models, while largely overlooking EAs. This imbalance poses a challenge to the long-term development of SAEAs. Among various SAEAs, surrogate-assisted Differential Evolution (SADE) is widely favored by researchers due to the competitive performance of DE in evolutionary Computation. It has been broadly applied across diverse engineering and scientific domains. Nevertheless, there is still no work that systematically investigates the progress of SADE. To balance the research direction of SAEAs and fill the gap, this paper provides a comprehensive survey of SADE. Its contributions are summarized as follows: This paper first introduces the general optimization framework of SAEAs and briefly reviews the research directions and advances of its key components. Next, a comprehensive survey of SADE is conducted, covering commonly used surrogate models and DE algorithms. It also examines how existing SADE algorithms use DE, performance evaluation methods, and real-world applications. Finally, future challenges and potential research directions are discussed. We hope this work will draw attention to EAs and inspire further research to advance related fields.
Recently, surrogate-assisted evolutionary algorithms (SAEAs) have been widely employed in solving Expensive Optimization Problems (EOPs) due to their efficiency in obtaining satisfactory solutions with limited resourc...
详细信息
Recently, surrogate-assisted evolutionary algorithms (SAEAs) have been widely employed in solving Expensive Optimization Problems (EOPs) due to their efficiency in obtaining satisfactory solutions with limited resources. By leveraging historical data to construct surrogate models for approximation, SAEAs can significantly reduce the number of expensive fitness evaluations for EOPs. A hierarchical SAEA optimization framework based on evolutionary sampling methods has achieved remarkable success in High-dimensional EOPs (HEOPs), which can effectively balance the exploration and exploitation capabilities. However, the majority of existing hierarchical SAEAs focus on either switching between different sampling strategies or enhancing a single sampling strategy, potentially overlooking the potential to improve multiple sampling strategies simultaneously. In this paper, we propose a surrogate-assisted Differential Evolution with Multiple Sampling Mechanisms (SADE-MSM) to tackle HEOPs, incorporating three sampling strategies with different mechanisms. The contributions of SADE-MSM are summarized as follows: 1) A centroid sampling method is applied before iterative optimization to enhance the early exploration ability;2) An improved global prescreening sampling strategy is introduced to balance the exploration and exploitation capabilities;3) A local search sampling with the adaptive optimal region strategy is proposed, significantly improving the exploitation ability. To validate the performance of SADEMSM, we compared it with the state-of-the-art SAEAs on benchmark problems with dimensions ranging from 30 to 500. Experimental results demonstrate that SADE-MSM has a significant performance superiority.
The design of microwave metasurface absorbers (MMAs) is complicated because numerous design parameters require high-performance optimization algorithms. In this article, a random forest-assisted improved estimation of...
详细信息
The design of microwave metasurface absorbers (MMAs) is complicated because numerous design parameters require high-performance optimization algorithms. In this article, a random forest-assisted improved estimation of distribution algorithm (RFIEDA) is proposed. RFIEDA aims to obtain a high-quality MMA design with a limited number of exact expensive evaluations, where the geometric parameters and MMA unit patterns are both optimized. To address the mixed variable nature of geometric parameters and MMA unit patterns, a coding method is presented to transform geometric parameters into binary sequences, effectively making them discrete like MMA unit patterns. A random forest (RF) model is employed to establish a mapping between design variables and the objective function. Improved estimation of distribution algorithm (IEDA) is used to globally search for the combination of MMA unit patterns and geometric parameters, which cooperated with RF to accelerate the convergence speed. Moreover, a model management strategy is introduced to identify candidate solutions from the individuals generated by the IEDA for the exact expensive evaluations. The performance of RFIEDA is demonstrated by a broadband MMA and a triple-band MMA.
Recently, surrogate-assisted evolutionary algorithms (SAEAs) received a lot of attention due to their excellent performance in handling expensive constrained optimization problems (ECOPs). However, most of them can on...
详细信息
Recently, surrogate-assisted evolutionary algorithms (SAEAs) received a lot of attention due to their excellent performance in handling expensive constrained optimization problems (ECOPs). However, most of them can only be used for solving problems that are low-dimensional and with only continuous variables. Therefore, a surrogate-assisted differential evolution for high-dimensional ECOPs with mixed-integer variables (SADE-HDMI) is proposed in this paper. Firstly, a Multiple Local Extremum based Sampling (MLES) method is designed, in which two sampling strategies focusing on constraints and objective functions are utilized alternatively based on iterative information, so that the feasible region and high-quality feasible solutions can be efficiently located. Secondly, a Diverse Population Generation Operation for Mixed-Integer Variables (DPMI) is devised to avoid the population from falling into a local optimal region, where the diversity of the population is maintained by selecting solutions with more diversity and limiting the number of solutions with the same integer variables in the population. Convergence and diversity can be well balanced under the help of these two operations. Finally, the performance of SADE-HDMI is validated on fifteen benchmarks and a real-world optimization problem. The optimization results demonstrate that SADE-HDMI can locate feasible solutions with 100% probability on these 16 problems, and it is superior to or similar to other three state-of-the-art algorithms on 15 out of 16 problems.
evolutionaryalgorithms are increasingly recognised as a viable computational approach for the automated optimisation of deep neural networks (DNNs) within artificial intelligence. This method extends to the training ...
详细信息
ISBN:
(纸本)9783031779404;9783031779411
evolutionaryalgorithms are increasingly recognised as a viable computational approach for the automated optimisation of deep neural networks (DNNs) within artificial intelligence. This method extends to the training of DNNs, an approach known as neuroevolution. However, neuroevolution is an inherently resource-intensive process, with certain studies reporting the consumption of thousands of GPU days for refining and training a single DNN network. To address the computational challenges associated with neuroevolution while still attaining good DNN accuracy, surrogate models emerge as a pragmatic solution. Despite their potential, the integration of surrogate models into neuroevolution is still in its early stages, hindered by factors such as the effective use of high-dimensional data and the representation employed in neuroevolution. In this context, we address these challenges by employing a suitable representation based on Linear Genetic Programming, denoted as NeuroLGP, and leveraging Kriging Partial Least Squares. The amalgamation of these two techniques culminates in our proposed methodology known as the NeuroLGP-surrogate Model (NeuroLGP-SM). For comparison purposes, we also code and use a baseline approach incorporating a repair mechanism, a common practice in neuroevolution. Notably, the baseline approach surpasses the renowned VGG-16 model in accuracy. Given the computational intensity inherent in DNN operations, a singular run is typically the norm. To evaluate the efficacy of our proposed approach, we conducted 96 independent runs spanning a duration of 4weeks. Significantly, our methodologies consistently outperform the baseline, with the SM model demonstrating superior accuracy or comparable results to the NeuroLGP approach. Noteworthy is the additional advantage that the SM approach exhibits a 25% reduction in computational requirements, further emphasising its efficiency for neuroevolution.
This paper develops a surrogate-assistedevolutionary programming (EP) algorithm for constrained expensive black-box optimization that can be used for high-dimensional problems with many black-box inequality constrain...
详细信息
This paper develops a surrogate-assistedevolutionary programming (EP) algorithm for constrained expensive black-box optimization that can be used for high-dimensional problems with many black-box inequality constraints. The proposed method does not use a penalty function and it builds surrogates for the objective and constraint functions. Each parent generates a large number of trial offspring in each generation. Then, the surrogate functions are used to identify the trial offspring that are predicted to be feasible with the best predicted objective function values or those with the minimum number of predicted constraint violations. The objective and constraint functions are then evaluated only on the most promising trial offspring from each parent, and the method proceeds in the same way as in a standard EP. In the numerical experiments, the type of surrogate used to model the objective and each of the constraint functions is a cubic radial basis function (RBF) augmented by a linear polynomial. The resulting RBF-assisted EP is applied to 18 benchmark problems and to an automotive problem with 124 decision variables and 68 black-box inequality constraints. The proposed method is much better than a traditional EP, a surrogate-assisted penalty-based EP, stochastic ranking evolution strategy, scatter search, and CMODE, and it is competitive with ConstrLMSRBF on the problems used.
暂无评论