The present study proposes a multi-objective framework for structure selection of nonlinear systems which are represented by polynomial NARX models. This framework integrates the key components of Multi-Criteria Decision Making (MCDM) which include preference handling, Multi-Objective Evolutionary Algorithms (MOEAs) and a posteriori selection. To this end, three well-known MOEAs such as NSGA-II, SPEA-II and MOEA/D are thoroughly investigated to determine if there exists any significant difference in their search performance. The sensitivity of all these MOEAs to various qualitative and quantitative parameters, such as the choice of recombination mechanism, crossover and mutation probabilities, is also studied. These issues are critically analyzed considering seven discrete-time and a continuous-time benchmark nonlinear system as well as a practical case study of non-linear wave-force modeling. The results of this investigation demonstrate that MOEAs can be tailored to determine the correct structure of nonlinear systems. Further, it has been established through frequency domain analysis that it is possible to identify multiple valid discrete-time models for continuous-time systems. A rigorous statistical analysis of MOEAs via performance sweet spots in the parameter space convincingly demonstrates that these algorithms are robust over a wide range of control parameters.
In the first and so far only mathematical runtime analysis of an estimation-of-distribution algorithm (EDA) on a multimodal problem, Hasen\"ohrl and Sutton (GECCO 2018) showed for any $k = o(n)$ that the compact genetic algorithm (cGA) with any hypothetical population size $\mu = \Omega(ne^{4k} + n^{3.5+\varepsilon})$ with high probability finds the optimum of the $n$-dimensional jump function with jump size $k$ in time $O(\mu n^{1.5} \log n)$. We significantly improve this result for small jump sizes $k \le \frac 1 {20} \ln n -1$. In this case, already for $\mu = \Omega(\sqrt n \log n) \cap \text{poly}(n)$ the runtime of the cGA with high probability is only $O(\mu \sqrt n)$. For the smallest admissible values of $\mu$, our result gives a runtime of $O(n \log n)$, whereas the previous one only shows $O(n^{5+\varepsilon})$. Since it is known that the cGA with high probability needs at least $\Omega(\mu \sqrt n)$ iterations to optimize the unimodal OneMx function, our result shows that the cGA in contrast to most classic evolutionary algorithms here is able to cross moderate-sized valleys of low fitness at no extra cost. For large $k$, we show that the exponential (in $k$) runtime guarantee of Hasen\"ohrl and Sutton is tight and cannot be improved, also not by using a smaller hypothetical population size. We prove that any choice of the hypothetical population size leads to a runtime that, with high probability, is at least exponential in the jump size $k$. This result might be the first non-trivial exponential lower bound for EDAs that holds for arbitrary parameter settings.
We propose a new approach for building recommender systems by adapting surrogate-assisted interactive genetic algorithms. A pool of user-evaluated items is used to construct an approximative model which serves as a surrogate fitness function in a genetic algorithm for optimizing new suggestions. The surrogate is used to recommend new items to the user, which are then evaluated according to the user's liking and subsequently removed from the search space. By updating the surrogate model after new recommendations have been evaluated by the user, we enable the model itself to evolve towards the user's preferences. In order to precisely evaluate the performance of that approach, the human's subjective evaluation is replaced by common continuous objective benchmark functions for evolutionary algorithms. The system's performance is compared to a conventional genetic algorithm and random search. We show that given a very limited amount of allowed evaluations on the true objective, our approach outperforms these baseline methods.
Dynamic optimization, for which the objective functions change over time, has attracted intensive investigations due to the inherent uncertainty associated with many real-world problems. For its robustness with respect to noise, Evolutionary Algorithms (EAs) have been expected to have great potential for dynamic optimization. On the other hand, EAs are also criticized for its high computational complexity, which appears to be contradictory to the core requirement of real-world dynamic optimization, i.e., fast adaptation (typically in terms of wall-clock time) to the environmental change. So far, whether EAs would indeed lead to a truly effective approach for real-world dynamic optimization remain unclear. In this paper, a new framework of employing EAs in the context of dynamic optimization is explored. We suggest that, instead of online evolving (searching) solutions for the ever-changing objective function, EAs are more suitable for acquiring an archive of solutions in an offline way, which could be adopted to construct a system to provide high-quality solutions efficiently in a dynamic environment. To be specific, we first re-formulate dynamic optimization problems as static set-oriented optimization problems. Then, a particular type of EAs, namely competitive coevolution, is employed to search for the archive of solutions in an adversarial way. The general framework is instantiated for continuous dynamic constrained optimization problems, and the empirical results showed the potential of the proposed framework.
Steganography algorithms facilitate communication between a source and a destination in a secret manner. This is done by embedding messages/text/data into images without impacting the appearance of the resultant images/videos. Steganalysis is the science of determining if an image has secret messages embedded/hidden in it. Because there are numerous steganography algorithms, and since each one of them requires a different type of steganalysis, the steganalysis process is extremely challenging. Thus, researchers aim to develop one universal steganalysis to detect all known and unknown steganography algorithms, ideally in real-time. Universal steganalysis extracts a large number of features to distinguish stego images from cover images. However, the increase in features leads to the problem of the curse of dimensionality (CoD), which is considered to be an NP-hard problem. This COD problem additionally makes real-time steganalysis hard. A large number of features generates large datasets for which machine learning cannot generate an optimal model. Generating a machine learning based model also takes a long time which makes real-time processing appear impossible in any optimization for time-intensive fields such as visual computing. Possible solutions for CoD are deep learning and evolutionary algorithms that overcome the machine learning limitations. In this study, we investigate previously developed evolutionary algorithms for boosting real-time image processing and argue that they provide the most promising solutions for the CoD problem.
Evolutionary algorithms (EAs) are a sort of nature-inspired metaheuristics, which have wide applications in various practical optimization problems. In these problems, objective evaluations are usually inaccurate, because noise is almost inevitable in real world, and it is a crucial issue to weaken the negative effect caused by noise. Sampling is a popular strategy, which evaluates the objective a couple of times, and employs the mean of these evaluation results as an estimate of the objective value. In this work, we introduce a novel sampling method, median sampling, into EAs, and illustrate its properties and usefulness theoretically by solving OneMax, the problem of maximizing the number of 1s in a bit string. Instead of the mean, median sampling employs the median of the evaluation results as an estimate. Through rigorous theoretical analysis on OneMax under the commonly used onebit noise, we show that median sampling reduces the expected runtime exponentially. Next, through two special noise models, we show that when the 2-quantile of the noisy fitness increases with the true fitness, median sampling can be better than mean sampling; otherwise, it may fail and mean sampling can be better. The results may guide us to employ median sampling properly in practical applications.
Pseudo-Boolean monotone functions are unimodal functions which are trivial to optimize for some hillclimbers, but are challenging for a surprising number of evolutionary algorithms (EAs). A general trend is that EAs are efficient if parameters like the mutation rate are set conservatively, but may need exponential time otherwise. In particular, it was known that the $(1+1)$-EA and the $(1+\lambda)$-EA can optimize every monotone function in pseudolinear time if the mutation rate is $c/n$ for some $c<1$, but they need exponential time for some monotone functions for $c>2.2$. The second part of the statement was also known for the $(\mu+1)$-EA. In this paper we show that the first statement does not apply to the $(\mu+1)$-EA. More precisely, we prove that for every constant $c>0$ there is a constant integer $\mu_0$ such that the $(\mu+1)$-EA with mutation rate $c/n$ and population size $\mu_0\le\mu\le n$ needs superpolynomial time to optimize some monotone functions. Thus, increasing the population size by just a constant has devastating effects on the performance. This is in stark contrast to many other benchmark functions on which increasing the population size either increases the performance significantly, or affects performance mildly. The reason why larger populations are harmful lies in the fact that larger populations may temporarily decrease selective pressure on parts of the population. This allows unfavorable mutations to accumulate in single individuals and their descendants. If the population moves sufficiently fast through the search space, such unfavorable descendants can become ancestors of future generations, and the bad mutations are preserved. Remarkably, this effect only occurs if the population renews itself sufficiently fast, which can only happen far away from the optimum. This is counter-intuitive since usually optimization gets harder as we approach the optimum.
Multiple-TSP, also abbreviated in the literature as mTSP, is an extension of the Traveling Salesman Problem that lies at the core of many variants of the Vehicle Routing problem of great practical importance. The current paper develops and experiments with Self Organizing Maps, Evolutionary Algorithms and Ant Colony Systems to tackle the MinMax formulation of the Single-Depot Multiple-TSP. Hybridization between the neural network approach and the two meta-heuristics shows to bring significant improvements, outperforming results reported in the literature on a set of problem instances taken from TSPLIB.
We introduce a new benchmark problem called Deceptive Leading Blocks (DLB) to rigorously study the runtime of the Univariate Marginal Distribution Algorithm (UMDA) in the presence of epistasis and deception. We show that simple Evolutionary Algorithms (EAs) outperform the UMDA unless the selective pressure $\mu/\lambda$ is extremely high, where $\mu$ and $\lambda$ are the parent and offspring population sizes, respectively. More precisely, we show that the UMDA with a parent population size of $\mu=\Omega(\log n)$ has an expected runtime of $e^{\Omega(\mu)}$ on the DLB problem assuming any selective pressure $\frac{\mu}{\lambda} \geq \frac{14}{1000}$, as opposed to the expected runtime of $\mathcal{O}(n\lambda\log \lambda+n^3)$ for the non-elitist $(\mu,\lambda)~\text{EA}$ with $\mu/\lambda\leq 1/e$. These results illustrate inherent limitations of univariate EDAs against deception and epistasis, which are common characteristics of real-world problems. In contrast, empirical evidence reveals the efficiency of the bi-variate MIMIC algorithm on the DLB problem. Our results suggest that one should consider EDAs with more complex probabilistic models when optimising problems with some degree of epistasis and deception.
In the last years, reinforcement learning received a lot of attention. One method to solve reinforcement learning tasks is Neuroevolution, where neural networks are optimized by evolutionary algorithms. A disadvantage of Neuroevolution is that it can require numerous function evaluations, while not fully utilizing the available information from each fitness evaluation. This is especially problematic when fitness evaluations become expensive. To reduce the cost of fitness evaluations, surrogate models can be employed to partially replace the fitness function. The difficulty of surrogate modeling for Neuroevolution is the complex search space and how to compare different networks. To that end, recent studies showed that a kernel based approach, particular with phenotypic distance measures, works well. These kernels compare different networks via their behavior (phenotype) rather than their topology or encoding (genotype). In this work, we discuss the use of surrogate model-based Neuroevolution (SMB-NE) using a phenotypic distance for reinforcement learning. In detail, we investigate a) the potential of SMB-NE with respect to evaluation efficiency and b) how to select adequate input sets for the phenotypic distance measure in a reinforcement learning problem. The results indicate that we are able to considerably increase the evaluation efficiency using dynamic input sets.
Designing evolutionary algorithms capable of uncovering highly evolvable representations is an open challenge; such evolvability is important because it accelerates evolution and enables fast adaptation to changing circumstances. This paper introduces evolvability ES, an evolutionary algorithm designed to explicitly and efficiently optimize for evolvability, i.e. the ability to further adapt. The insight is that it is possible to derive a novel objective in the spirit of natural evolution strategies that maximizes the diversity of behaviors exhibited when an individual is subject to random mutations, and that efficiently scales with computation. Experiments in 2-D and 3-D locomotion tasks highlight the potential of evolvability ES to generate solutions with tens of thousands of parameters that can quickly be adapted to solve different tasks and that can productively seed further evolution. We further highlight a connection between evolvability and a recent and popular gradient-based meta-learning algorithm called MAML; results show that evolvability ES can perform competitively with MAML and that it discovers solutions with distinct properties. The conclusion is that evolvability ES opens up novel research directions for studying and exploiting the potential of evolvable representations for deep neural networks.
The performance of deep neural networks, such as Deep Belief Networks formed by Restricted Boltzmann Machines (RBMs), strongly depends on their training, which is the process of adjusting their parameters. This process can be posed as an optimization problem over n dimensions. However, typical networks contain tens of thousands of parameters, making this a High-Dimensional Problem (HDP). Although different optimization methods have been employed for this goal, the use of most of the Evolutionary Algorithms (EAs) becomes prohibitive due to their inability to deal with HDPs. For instance, the Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) which is regarded as one of the most effective EAs, exhibits the enormous disadvantage of requiring $O(n^2)$ memory and operations, making it unpractical for problems with more than a few hundred variables. In this paper, we introduce a novel EA that requires $O(n)$ operations and memory, but delivers competitive solutions for the training stage of RBMs with over one million variables, when compared against CMA-ES and the Contrastive Divergence algorithm, which is the standard method for training RBMs.
Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models.Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models.Since it usually requires a certain amount of data (i.e. the candidate solutions generated by the algorithms) for model training, the performance deteriorates rapidly with the increase of the problem scales, due to the curse of dimensionality.To address this issue, we propose a multi-objective evolutionary algorithm driven by the generative adversarial networks (GANs).At each generation of the proposed algorithm, the parent solutions are first classified into \emph{real} and \emph{fake} samples to train the GANs; then the offspring solutions are sampled by the trained GANs.Thanks to the powerful generative ability of the GANs, our proposed algorithm is capable of generating promising offspring solutions in high-dimensional decision space with limited training data.The proposed algorithm is tested on 10 benchmark problems with up to 200 decision variables.Experimental results on these test problems demonstrate the effectiveness of the proposed algorithm.
Lattice-based cryptography has recently emerged as a prominent candidate for secure communication in the quantum age. Its security relies on the hardness of certain lattice problems, and the inability of known lattice algorithms, such as lattice sieving, to solve these problems efficiently. In this paper we investigate the similarities between lattice sieving and evolutionary algorithms, how various improvements to lattice sieving can be viewed as applications of known techniques from evolutionary computation, and how other evolutionary techniques can benefit lattice sieving in practice.
Quality-diversity (QD) algorithms search for a set of good solutions which cover a space as defined by behavior metrics. This simultaneous focus on quality and diversity with explicit metrics sets QD algorithms apart from standard single- and multi-objective evolutionary algorithms, as well as from diversity preservation approaches such as niching. These properties open up new avenues for artificial intelligence in games, in particular for procedural content generation. Creating multiple systematically varying solutions allows new approaches to creative human-AI interaction as well as adaptivity. In the last few years, a handful of applications of QD to procedural content generation and game playing have been proposed; we discuss these and propose challenges for future work.
The installed amount of renewable energy has expanded massively in recent years. Wave energy, with its high capacity factors has great potential to complement established sources of solar and wind energy. This study explores the problem of optimising the layout of advanced, three-tether wave energy converters in a size-constrained farm in a numerically modelled ocean environment. Simulating and computing the complicated hydrodynamic interactions in wave farms can be computationally costly, which limits optimisation methods to have just a few thousand evaluations. For dealing with this expensive optimisation problem, an adaptive neuro-surrogate optimisation (ANSO) method is proposed that consists of a surrogate Recurrent Neural Network (RNN) model trained with a very limited number of observations. This model is coupled with a fast meta-heuristic optimiser for adjusting the model's hyper-parameters. The trained model is applied using a greedy local search with a backtracking optimisation strategy. For evaluating the performance of the proposed approach, some of the more popular and successful Evolutionary Algorithms (EAs) are compared in four real wave scenarios (Sydney, Perth, Adelaide and Tasmania). Experimental results show that the adaptive neuro model is competitive with other optimisation methods in terms of total harnessed power output and faster in terms of total computational costs.
Among many evolutionary algorithms, differential evolution (DE) has received much attention over the last two decades. DE is a simple yet powerful evolutionary algorithm that has been used successfully to optimize various real-world problems. Since it was introduced, many researchers have developed new methods for DE, and one of them makes use of a mutation based on the Cauchy distribution to increase the convergence speed of DE. The method monitors the results of each individual in the selection operator and performs the Cauchy mutation on consecutively failed individuals, which generates mutant vectors by perturbing the best individual with the Cauchy distribution. Therefore, the method can locate the consecutively failed individuals to new positions close to the best individual. Although this approach is interesting, it fails to take into account establishing a balance between exploration and exploitation. In this paper, we propose a sigmoid based parameter control that alters the failure threshold for performing the Cauchy mutation in a time-varying schedule, which can establish a good ratio between exploration and exploitation. Experiments and comparisons have been done with six conventional and six advanced DE variants on a set of 30 benchmark problems, which indicate that the DE variants assisted by the proposed algorithm are highly competitive, especially for multimodal functions.
This article describes the application of soft computing methods for solving the problem of locating garbage accumulation points in urban scenarios. This is a relevant problem in modern smart cities, in order to reduce negative environmental and social impacts in the waste management process, and also to optimize the available budget from the city administration to install waste bins. A specific problem model is presented, which accounts for reducing the investment costs, enhance the number of citizens served by the installed bins, and the accessibility to the system. A family of single- and multi-objective heuristics based on the PageRank method and two mutiobjective evolutionary algorithms are proposed. Experimental evaluation performed on real scenarios on the cities of Montevideo (Uruguay) and Bahia Blanca (Argentina) demonstrates the effectiveness of the proposed approaches. The methods allow computing plannings with different trade-off between the problem objectives. The computed results improve over the current planning in Montevideo and provide a reasonable budget cost and quality of service for Bahia Blanca.
Evolutionary algorithm research and applications began over 50 years ago. Like other artificial intelligence techniques, evolutionary algorithms will likely see increased use and development due to the increased availability of computation, more robust and available open source software libraries, and the increasing demand for artificial intelligence techniques. As these techniques become more adopted and capable, it is the right time to take a perspective of their ability to integrate into society and the human processes they intend to augment. In this review, we explore a new taxonomy of evolutionary algorithms and resulting classifications that look at five main areas: the ability to manage the control of the environment with limiters, the ability to explain and repeat the search process, the ability to understand input and output causality within a solution, the ability to manage algorithm bias due to data or user design, and lastly, the ability to add corrective measures. These areas are motivated by today's pressures on industry to conform to both societies concerns and new government regulatory rules. As many reviews of evolutionary algorithms exist, after motivating this new taxonomy, we briefly classify a broad range of algorithms and identify areas of future research.
This paper presents a technique called evolving self-supervised neural networks - neural networks that can teach themselves, intrinsically motivated, without external supervision or reward. The proposed method presents some sort-of paradigm shift, and differs greatly from both traditional gradient-based learning and evolutionary algorithms in that it combines the metaphor of evolution and learning, more specifically self-learning, together, rather than treating these phenomena alternatively. I simulate a multi-agent system in which neural networks are used to control autonomous foraging agents with little domain knowledge. Experimental results show that only evolved self-supervised agents can demonstrate some sort of intelligent behaviour, but not evolution or self-learning alone. Indications for future work on evolving intelligence are also presented.