Proceedings of the Genetic and Evolutionary Computation Conference Companion最新文献_第2页

Evolutionary computation and evolutionary deep learning for image analysis, signal processing and pattern recognition 用于图像分析、信号处理和模式识别的进化计算和进化深度学习

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3533636

Mengjie Zhang, S. Cagnoni

引用次数: 0

A chaotic parallel antlion optimization algorithm for feature selection 特征选择的混沌并行蚁群优化算法

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528913

Xun Zhou, Hongwei Chen, Dewei Shi

引用次数: 0

Generating failing test suites for quantum programs with search (hot off the press track at GECCO 2022) 使用搜索为量子程序生成失败的测试套件(GECCO 2022即将发布)

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3534067

Xinyi Wang, Paolo Arcaini, T. Yue, Shaukat Ali

{"title":"Generating failing test suites for quantum programs with search (hot off the press track at GECCO 2022)","authors":"Xinyi Wang, Paolo Arcaini, T. Yue, Shaukat Ali","doi":"10.1145/3520304.3534067","DOIUrl":"https://doi.org/10.1145/3520304.3534067","url":null,"abstract":"The inherent complexity of quantum programs, due to features such as superposition and entanglement, makes their testing particularly challenging. To tackle these challenges, we present a search-based approach, called Quantum Search-Based Testing (QuSBT), for automatically generating test suites of a given size that possibly expose failures of the quantum program under test. QuSBT encodes a test suite as a search individual, and tries to maximize the objective function that counts the number of failing tests in the test suite. Due to non-deterministic nature of quantum programs, the approach repeats the execution of each test multiple times, and uses suitable statistical tests to assess if a test passes or fails. QuSBT employs a genetic algorithm to perform the search. Experiments on 30 faulty quantum programs show that QuSBT is statistically better than random search, and is able to efficiently generate maximal failing test suites. This is an extended abstract of the paper [1]: X. Wang, P. Arcaini, T. Yue, and S. Ali \"Generating Failing Test Suites for Quantum Programs With Search\", 13th International Symposium on Search-Based Software Engineering (SSBSE 2021).","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114518540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 23

On the potential of automated algorithm configuration on multi-modal multi-objective optimization problems 论多模态多目标优化问题自动算法配置的潜力

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528998

Jeroen G. Rook, H. Trautmann, Jakob Bossek, C. Grimme

引用次数: 1

Amaru

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.7312/part18438-004

O. Krauss

引用次数: 0

Learning to balance exploration and exploitation in pareto local search for multi-objective combinatorial optimization 学习多目标组合优化pareto局部搜索中探索与利用的平衡

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528906

Haotian Zhang, Jialong Shi, Jianyong Sun, Zongben Xu

{"title":"Learning to balance exploration and exploitation in pareto local search for multi-objective combinatorial optimization","authors":"Haotian Zhang, Jialong Shi, Jianyong Sun, Zongben Xu","doi":"10.1145/3520304.3528906","DOIUrl":"https://doi.org/10.1145/3520304.3528906","url":null,"abstract":"As a natural extension of local search, Pareto local search (PLS) is a basic building block in many state-of-the-art metaheuristics for multi-objective combinatorial optimization problems (MCOPs). However, the basic PLS suffers from a low convergence rate, since it always fully explores the neighborhood of each unexplored solution, which is unnecessary. Some studies tried to introduce heuristic design in PLS to balance exploration and exploitation. In this paper, we handle this issue by a learning based framework. In the framework, PLS applies the firstK strategy, namely it stops exploring a solution's neighborhood when it obtains K non-dominated solutions, where K is adaptively controlled by a neural network based on observations collected during the search. Training the neural network is modeled as a reinforcement learning problem. Thus the proposed PLS variant is called PLSNN. In the experiments, we compared the performance of PLS, PLSNN and several PLS variants with heuristic design on the multi-objective unconstrained binary quadratic programming problem (mUBQP). The experimental results show that PLSNN performed significantly better than its counterparts on all test instances.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"04 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130338445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Evolutionary generation of metamorphic relations for cyber-physical systems 网络物理系统中变质关系的演化生成

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3534077

J. Ayerdi, Valerio Terragni, Aitor Arrieta, P. Tonella, Goiuria Sagardui Mendieta, Maite Arratibel

引用次数: 2

Probabilistic reasoning as quadratic unconstrained binary optimization 二次型无约束二元优化的概率推理

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3534005

M. Baioletti

引用次数: 1

One-shot optimization for vehicle dynamics control systems: towards benchmarking and exploratory landscape analysis 车辆动力学控制系统的一次性优化:走向标杆与探索性景观分析

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3533979

André Thomaser, Anna V. Kononova, M. Vogt, Thomas Bäck

{"title":"One-shot optimization for vehicle dynamics control systems: towards benchmarking and exploratory landscape analysis","authors":"André Thomaser, Anna V. Kononova, M. Vogt, Thomas Bäck","doi":"10.1145/3520304.3533979","DOIUrl":"https://doi.org/10.1145/3520304.3533979","url":null,"abstract":"Many real-world black-box optimization problems from industry are computationally expensive. Due to the advantage in wall-clock time, fully parallel sampling (one-shot search) is therefore often chosen over iterative search and adaptive sampling approaches. Our contribution shows how using a surrogate model (one-shot optimization with surrogate) can enhance the best solution found within the initial sample, requiring no further problem evaluations. We test several surrogate types for one-shot optimization on a real-world problem from the field of vehicle dynamics control systems and the 24 well-known BBOB benchmark test functions. For the real-world problem and most of the benchmark functions considered, a multi-layer perceptron (neural network) as surrogate model for one-shot optimization leads to worse solutions than the one-shot search, in contrast to random forest and support vector machine. Moreover, our results show that mean squared error as a commonly used quality metrics for regression models is not feasible for selecting a surrogate model for one-shot optimization. To characterize the considered problems and to assess the similarity between the real-world problem and the benchmark functions, exploratory landscape analysis was performed. We provide some guidance on how to utilize this information to select a surrogate type for specific problems.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121300202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Py2Cy

Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3534037

J. Zhong, Max Hort, Federica Sarro

引用次数: 0