Evolutionary Search Research Articles

Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing

Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing

An Adversarial Approach for Automated Pokémon Team Building and Metagame Balance

Meta-game balance is a crucial task in game development, and automation of this process could assist game developers by vastly reducing time costs. We explore and evaluate a meta-game balance model over the recently proposed VGC AI Competition Framework. We propose an adversarial model where team builder agents try to maximize their win rate by narrowing to the most optimal team configurations, resulting in a reduction of the diversity of Pokémon employed, while a balancing agent re-adapts the Pokémon inner attributes to incentive the team builder agents to incorporate a greater variety of Pokémon into their teams increasing the meta-game's overall diversity and balance. one Furthermore, we developed multiple team builder agents divided into two groups: the first group assumes that individual Pokémon advantages are the primary factor to determine the outcome of game matches; the second group also exploits the implicit synergy between teammates. These agents make use of meta-gaming, linear optimization, and evolutionary search to find strong combinations against the current meta-game. The strongest team builder is faced against the team meta-game balance agent for its evaluation. Deep learning is also employed to predict the outcome of matches and recommend constructive elements of teams.

Inverse Hessian by stochastic projection and application to system identification in nonlinear mechanics of solids

Parameter identification in nonlinear mechanics of solids, a class of non-convex optimization problems of significant interest, often has to balance fast convergence with enhanced exploration. Local optimization schemes based on Newton or quasi-Newton updates cannot tread this fine balance. A similar limitation also applies to many derivative-free global evolutionary searches that typically end up with slower convergence. Notwithstanding a relatively rapid convergence around a local optimum, schemes using classical gradients require that the objective function be smooth. Thus, applied to real-world scenarios, these algorithms face challenges such as non-smoothness including discontinuities in the objective function and costly evaluations of gradients or Hessians, whenever possible. Based on a novel stochastic projection to estimate inverse Hessians, this work aims at generalizing a fast Newton-type local search whilst retaining capabilities of noise-assisted exploration in non-convex optimization. In principle, such a meeting of the best of both worlds in optimization should provide for a powerful paradigm shift, offering a versatile and robust tool for solving complex identification and variational problems arising in nonlinear mechanics of solids. The approach is well-suited even for cases where the objective function is implicitly defined and not amenable to explicit evaluation. In a first implementation of our proposal, we assess its performance against a few benchmark non-convex problems. Finally, we solve a parameter estimation problem for an isotropic and incompressible hyperelastic material.

An enhanced sparrow search swarm optimizer via multi-strategies for high-dimensional optimization problems

With the development of science and technology, high-dimensional global optimization problems have become increasingly prevalent for scientific research and engineering, such as gene recognition, vehicle routing, job scheduling, and network topology. These problems are typically characterized by enormous and complex search spaces and numerous local minima, making it challenging to find the global optimal solution with limited computing resources. This paper introduces an enhanced sparrow search swarm optimizer (ESSSO) based on a bio-mimetic method. The ESSSO employs an adaptive sinusoidal walk strategy based on the von Mises distribution, a learning strategy utilizing roulette wheel selection, a two-stage evolution strategy, and a selection mutation strategy to address these issues. The proposed sinusoidal walk strategy, grounded in the von Mises distribution, supports a balanced evolutionary search. This mechanism disperses the individuals in a swarm in various directions based on a circular normal distribution. It then leads the search and adaptively adjusts their step sizes according to the size of the search domain during each generation of evolution. The learning strategy, based on roulette wheel selection, enhances the diversity of the population and improves the global search capability of the algorithm during the initial iterations. The two-stage evolution strategy involves a sine-learning mechanism based on the von Mises distribution and an adaptive mutation mechanism. The former is designed to boost the convergence speed of ESSSO, while the latter prevents ESSSO from getting trapped in a local optimum. Additionally, the selection mutation strategy further enhances convergence speed while maintaining population diversity. These strategies promote exploration in the early stages of evolution and exploitation in the later stages, enabling a well-balanced search for optimal solutions. We conducted comprehensive experiments two standard benchmark sets (i.e., CEC2010 and CEC2013), antenna array optimization, feature selection, and four engineering design problems. The results indicate that ESSSO outperforms ten comparison algorithms, especially in scenarios with smaller population sizes. This confirms its effectiveness in high-dimensional global optimization tasks and demonstrates that it can achieve better results with less computational resource consumption.

Remarkable Optoelectronic Characteristics of Synthesizable Square‐Octagon Haeckelite Structures: Machine Learning Materials Discovery

AbstractThe research explores new compounds with structures similar to square‐octagonal beryllium oxide, commonly known as Haeckelites. The goal is to identify semiconducting variations compounds that can be synthesized and show promising potential in optoelectronic devices. Start with 1083 binary Haeckelite structures, and to test the synthesis potential of these materials quickly, develop new descriptors and use machine learning techniques. As a result, it identifies a subset of 350 materials with suitable properties in terms of phase stability and electronic perspective. These materials are further investigated to analyze their electronic structure and phase stability, which are determined through density functional theory calculations. The phase stabilities of the predicted semiconducting Haeckelites are also compared to other binary compounds using an evolutionary structure search algorithm. The comprehensive methodology also includes examining the dynamic stabilities through phonon calculations and mechanical properties through elastic constant calculations. Eventually, 13 new Haeckelite compounds are discovered, demonstrating exceptional stability and performance in electronic tests. Among these compounds, eight have shown remarkable absorption coefficients and are considered promising candidates with high reflectivity. Additionally, they have exhibited high electron mobility. These findings strongly suggest the potential of these compounds for synthesis and their application in optoelectronic devices.

Evolutionary Search for Stochastic Optimization with Binary Choice Relations Under Fuzzy Modeling

Evolutionary Search for Stochastic Optimization with Binary Choice Relations Under Fuzzy Modeling

A Dynamic Tasking-Based Evolutionary Algorithm for Bi-Objective Feature Selection

Feature selection in classification is a complex optimization problem that cannot be solved in polynomial time. Bi-objective feature selection, aiming to minimize both selected features and classification errors, is challenging due to the conflict between objectives, while one of the most effective ways to tackle this is to use multi-objective evolutionary algorithms. However, very few of these have ever reflected an evolutionary multi-tasking framework, despite the implicit parallelism offered by the population-based search characteristic. In this paper, a dynamic multi-tasking-based multi-objective evolutionary algorithm (termed DTEA) is proposed for handling bi-objective feature selection in classification, which is not only suitable for datasets with relatively lower dimensionality of features, but is also suitable for datasets with relatively higher dimensionality of features. The role and influence of multi-tasking on multi-objective evolutionary feature selection were studied, and a dynamic tasking mechanism is proposed to self-adaptively assign multiple evolutionary search tasks by intermittently analyzing the population behaviors. The efficacy of DTEA is tested on 20 classification datasets and compared with seven state-of-the-art evolutionary algorithms. A component contribution analysis was also conducted by comparing DTEA with its three variants. The empirical results show that the dynamic-tasking mechanism works efficiently and enables DTEA to outperform other algorithms on most datasets in terms of both optimization and classification.

Machine learning methods for background potential estimation in 2DEGs

Two-dimensional electron gases (2DEGs) can show exceptional carrier mobility, making them promising candidates for future quantum technologies. However, impurities and defects can significantly degrade their performance, impacting transport, conductivity, and coherence times. We leverage scanning gate microscopy (SGM) and machine learning approaches to extract the potential landscape of 2DEGs from SGM data. We compare three techniques: image-to-image translation with generative adversarial networks (GANs), cellular neural networks (CNNs), and an evolutionary search algorithm. Notably, the evolutionary approach outperforms both alternatives in defect identification and analysis. This work clarifies the interaction between defects and 2DEG properties, demonstrating the potential of machine learning for understanding and manipulating quantum materials, facilitating advancements in quantum computing and nanoelectronics.

A multi-objective optimization framework for determining optimal chemotherapy dosing and treatment duration

Traditional randomized clinical trials are regarded as the gold standard for assessing the efficacy of chemotherapy. However, this procedure has drawbacks such as high cost, time consumption, and limited patient exploration of treatment regimens. We develop a multi-objective optimization-based framework to address these limitations and determine the best chemotherapy dosing and treatment duration. The proposed framework uses patient-specific biological parameters to create a mathematical model of cell population dynamics in the patient’s body. The framework employs evolutionary heuristic search methods (simulated annealing and genetic algorithms) and a prescriptive analytics approach to optimize therapy sessions that transition from treatment to relaxation. We carefully adjust the chemotherapy dose during treatment to reduce tumor cells while preserving host cells (such as effector-immune cells). We strategically time the relaxation sessions to aid recovery, considering the ability of tumors and healthy cells to regenerate. We use a combined optimization method to determine the length of the session and the amount of drug to be administered. We compare quadratic and linear optimal control solvers for drug administration while genetic algorithms and simulated annealing are used to optimize session length. This approach is especially important in limited healthcare resources, ensuring efficient allocation while accurately identifying high-risk patients to optimize resource allocation and utilization.

Exploration of the two-dimensional transition metal phosphide MoP2 as anode for Na/K ion batteries

Transition metal phosphides are regarded to be potential anode materials for alkali metal ion batteries with abundant availability of the constituent elements. However, the volume changes and resulting structure deterioration during the charge-discharge process are challenges. Using evolutionary search combined with ab initio calculations, we discover a dynamically, thermally, and mechanically stable MoP2 monolayer, which turns out to be an excellent anode material for Na-ion batteries providing a high specific capacity of 339 mA h g−1, low diffusion barrier of 0.12 eV, and low open-circuit voltage of 0.48 V. The volume expansion (125%) is found to be decisively smaller than in the case of black phosphorus (443%), for example.

Evolutionary Search and Theoretical Study of Silicene Grain Boundaries' Mechanical Properties.

Defects such as grain boundaries (GBs) are almost inevitable during the synthesis process of 2D materials. To take advantage of the fascinating properties of 2D materials, understanding the nature and impact of various GB structures on pristine 2D sheets is crucial. In this work, using an evolutionary algorithm search, we predict a wide variety of silicene GB structures with very different atomic structures compared with those found in graphene or hexagonal boron-nitride. Twenty-one GBs with the lowest energy were validated by density functional theory (DFT), a majority of which were previously unreported to our best knowledge. Based on the diversity of the GB predictions, we found that the formation energy and mechanical properties can be dramatically altered by adatom positions within a GB and certain types of atomic structures, such as four-atom rings. To study the mechanical behavior of these GBs, we apply strain to the GB structures stepwise and use DFT calculations to investigate the mechanical properties of 9 representative structures. It is observed that GB structures based on pentagon-heptagon pairs are likely to have similar or higher in-plane stiffness and strength compared to the zigzag orientation of pristine silicene. However, an adatom located at the hollow site of a heptagon ring can significantly deteriorate the mechanical strength. For all of the structures, the in-plane stiffness and strength were found to decrease with increasing formation energy. For the failure behavior of GB structures, it was found that GB structures based on pentagon-heptagon pairs have failure behavior similar to that of graphene. We also found that the GB structures with atoms positioned outside of the 2D plane tend to experience phase transitions before failure. Utilizing the evolutionary algorithm, we locate diverse silicene GBs and obtain useful information about their mechanical properties.

DNA Sequences Under Multiple Guanine-Cytosine (GC) Base Pairs Constraint.

DNA computing is a new computing method that has high efficiency in solving large-scale nonlinear and Non-deterministic Polynomial complete problems. The design of DNA sequences is an important step in DNA computing, and the quality of the DNA sequences directly affects the accuracy of DNA computing results. Efficiently designing high-quality DNA sequences is currently a significant challenge. In order to improve the efficiency of DNA sequence design, a sparrow evolutionary search algorithm (SESA) is proposed by us. It inherits the fast convergence of the sparrow search algorithm and avoids the situation that the sparrow search algorithm is prone to fall into a local optimum, which greatly improves the search performance of the algorithm on discrete numerical problems. In order to improve the quality of DNA sequence, a new constraint, multiple GC constraint, has been proposed in this paper. Simulated experiments in NUPACK show that this constraint can greatly improve the quality of the DNA sequences designed by us. Compared with previous results, our DNA sequences have better stability.

Evolutionary Multitasking for Costly Task Offloading in Mobile-Edge Computing Networks

The offloading of computation-intensive tasks to an edge server near resource-constrained mobile devices can provide improved application performance and user experience. However, with the rapid growth of mobile devices connected to the edge server, it is challenging to directly obtain an optimal task offloading scheme due to increasing computational cost and problem scale. In this study, we model the costly task offloading problem (CTOP) in mobile edge computing networks to achieve efficient joint optimization of energy consumption and processing latency for mobile devices. Inspired by the success of evolutionary multitasking in solving complex optimization problems by leveraging the experience of simple optimization problems, we develop a novel multitasking framework whose effectiveness is demonstrated in solving the CTOP. In this framework, auxiliary tasks are created to optimize the local processing overhead and the edge processing overhead of task offloading. On this basis, we propose an effective multitask evolutionary algorithm that includes segmented knowledge transfer and auxiliary task update. Specifically, source and extended decision variables are considered as different knowledge to be utilized, while the auxiliary tasks are allowed to be updated dynamically. Related knowledge that is learned from cheap and simple auxiliary tasks promotes the evolutionary search for CTOP. Experimental results verify the effectiveness of knowledge transfer. Compared to existing multitasking and single-tasking algorithms, the proposed algorithm shows competitive performance in CTOP instances and achieves better comprehensive performance in terms of energy consumption and processing latency.

HPB3C-3PG algorithm: A new hybrid global optimization algorithm and its application to plant classification

This paper proposes a hybrid bio-inspired search and optimization algorithm that combines the strengths of the PB3C (Parallel Big Bang Big Crunch) and 3PGA (3 Parent Genetic Algorithm) algorithms. The hybrid algorithm employs a single population-based evolutionary search coupled with multi-population parallel processing techniques to address optimization problems. The proposed algorithm is implemented in MATLAB software. We evaluate the performance of the proposed algorithm on the CEC2021 standard test bench suite. The performance of the proposed approach is compared with that of the other nine algorithms. The comparative analysis shows that the proposed hybrid PB3C and 3PGA algorithms performed better than the other nine optimization algorithms. Furthermore, this chapter proposes an HPB3C-3PGA-based approach to evolve the near-optimal architecture of CNN. The proposed plant image classification approach is implemented in Python and compared with 12 other approaches. The proposed approach achieved an accuracy of 98.96% on the Mendeley dataset and 98.97% on the CVIP100 dataset. The proposed approach outperforms all other approaches for the plant leaf classification problem. This research significantly contributes to overcoming limitations in existing approaches, providing a robust solution for optimization problems and image classification tasks.

A Review on NEAT and Other Reinforcement Algorithms in Robotics

Artificial neural networks, or ANNs, find widespread use in real-world scenarios ranging from pattern recognition to robotics control. Choosing an architecture (which includes a model for the neurons) and a learning algorithm are important decisions when building a neural network for a particular purpose. An automated method for resolving these issues is provided by evolutionary search techniques.Genetic algorithms are used to artificially evolve neural networks in a process known as neuroevolution (NE), which has shown great promise in solving challenging reinforcement learning problems. This study offers a thorough review of the state-of-the-art techniques for evolving artificial neural networks (ANNs), with a focus on optimizing their performance-enhancing capabilities. Key Words: Artificial neural networks,Neuroevolution, NeuroEvolution of Augmenting Topologies,Brain computer interface.

EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration

Differentiable Architecture Search (DARTS) has achieved a rapid search for excellent architectures by optimizing architecture parameters through gradient descent. However, this efficiency comes with a significant challenge: the risk of premature convergence to local optima, resulting in subpar performance that falls short of expectations. To address this issue, we propose a novel and effective method called Evolutionary Gradient-Based Neural Architecture Search (EG-NAS). Our approach combines the strengths of both gradient descent and evolutionary strategy, allowing for the exploration of various optimization directions during the architecture search process. To begin with, we continue to employ gradient descent for updating network parameters to ensure efficiency. Subsequently, to mitigate the risk of premature convergence, we introduce an evolutionary strategy with global search capabilities to optimize the architecture parameters. By leveraging the best of both worlds, our method strikes a balance between efficient exploration and exploitation of the search space. Moreover, we have redefined the fitness function to not only consider accuracy but also account for individual similarity. This inclusion enhances the diversity and accuracy of the optimized directions identified by the evolutionary strategy. Extensive experiments on various datasets and search spaces demonstrate that EG-NAS achieves highly competitive performance at significantly low search costs compared to state-of-the-art methods. The code is available at https://github.com/caicaicheng/EG-NAS.

An evolutionary neural architecture search method based on performance prediction and weight inheritance

Evolutionary Neural Architecture Search (ENAS) algorithms attract great attention since they can automatically search for appropriate network architectures for a given task. However, most ENAS algorithms suffer from a prohibitive computational burden. Moreover, some of these approaches directly use performance predictors for evaluations, which may introduce inaccurate assessments and harm the evolution. To overcome these shortcomings, we propose an efficient ENAS algorithm named EPPGA. EPPGA employs a predictor to pre-select potentially high-performing offspring, enhancing the performance and accelerating the evolution. As the offspring will be further accurately evaluated, even potentially inaccurate predictions will not adversely affect the evolution. Furthermore, a weight inheritance method is suggested to accelerate the evaluation, and new genetic operations are developed to produce offspring that share a substantial proportion of beneficial genetic materials with one parent, improving the performance predictor's effectiveness and promoting weight inheritance. Finally, a new efficient backbone block structure is designed to facilitate the search for lightweight networks. The experimental results demonstrate that EPPGA is a highly competitive algorithm on three benchmarks in terms of accuracy, model size, and computational cost, reveal the superiority of the proposed block structure, and confirm the effectiveness of the proposed performance predictor and weight inheritance method.

Generalized Early Stopping in Evolutionary Direct Policy Search

Lengthy evaluation times are common in many optimization problems such as direct policy search tasks, especially when they involve conducting evaluations in the physical world, e.g. in robotics applications. Often when evaluating solution over a fixed time period it becomes clear that the objective value will not increase with additional computation time (for example when a two wheeled robot continuously spins on the spot). In such cases, it makes sense to stop the evaluation early to save computation time. However, most approaches to stop the evaluation are problem specific and need to be specifically designed for the task at hand. Therefore, we propose an early stopping method for direct policy search. The proposed method only looks at the objective value at each time step and requires no problem specific knowledge. We test the introduced stopping criterion in five direct policy search environments drawn from games, robotics and classic control domains, and show that it can save up to \(75\%\) of the computation time. We also compare it with problem specific stopping criteria and show that it performs comparably, while being more generally applicable.

PSE-Net: Channel pruning for Convolutional Neural Networks with parallel-subnets estimator

Channel Pruning is one of the most widespread techniques used to compress deep neural networks while maintaining their performances. Currently, a typical pruning algorithm leverages neural architecture search to directly find networks with a configurable width, the key step of which is to identify representative subnet for various pruning ratios by training a supernet. However, current methods mainly follow a serial training strategy to optimize supernet, which is very time-consuming. In this work, we introduce PSE-Net, a novel parallel-subnets estimator for efficient channel pruning. Specifically, we propose a parallel-subnets training algorithm that simulate the forward–backward pass of multiple subnets by droping extraneous features on batch dimension, thus various subnets could be trained in one round. Our proposed algorithm facilitates the efficiency of supernet training and equips the network with the ability to interpolate the accuracy of unsampled subnets, enabling PSE-Net to effectively evaluate and rank the subnets. Over the trained supernet, we develop a prior-distributed-based sampling algorithm to boost the performance of classical evolutionary search. Such algorithm utilizes the prior information of supernet training phase to assist in the search of optimal subnets while tackling the challenge of discovering samples that satisfy resource constraints due to the long-tail distribution of network configuration. Extensive experiments demonstrate PSE-Net outperforms previous state-of-the-art channel pruning methods on the ImageNet dataset while retaining superior supernet training efficiency. For example, under 300M FLOPs constraint, our pruned MobileNetV2 achieves 75.2% Top-1 accuracy on ImageNet dataset, exceeding the original MobileNetV2 by 2.6 units while only cost 30%/16% times than BCNet/AutoAlim.

Guided evolutionary neural architecture search with efficient performance estimation

Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures yield good results. This paper proposes GEA, a novel approach for guided NAS. GEA guides the evolution by exploring the search space by generating and evaluating several architectures in each generation at initialization stage using a zero-proxy estimator, where only the highest-scoring architecture is trained and kept for the next generation. Subsequently, GEA continuously extracts knowledge about the search space without increased complexity by generating several off-springs from an existing architecture at each generation. Moreover, GEA forces exploitation of the most performant architectures by descendant generation while simultaneously driving exploration through parent mutation and favouring younger architectures to the detriment of older ones. Experimental results demonstrate the effectiveness of the proposed method, and extensive ablation studies evaluate the importance of different parameters. Results show that GEA achieves competitive results on all data sets of NAS-Bench-101, NAS-Bench-201 and TransNAS-Bench-101 benchmarks, as well as in the DARTS search space.