检索结果-内蒙古大学图书馆

Selecting algorithms for large berth allocation problems

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2020年第3期283卷 844-862页

作者： Wawrzyniak, Jakub Drozdowski, Maciej Sanlaville, Eric Poznan Univ Tech Inst Comp Sci Poznan Poland Normandie Univ UNIHAVRE INSA Rouen UNIROUENLITIS F-76600 Le Havre France

This paper considers algorithm selection for the berth allocation problem (BAP) under algorithm runtime limits. BAP consists in scheduling ships on berths subject to ship ready times and size constraints, for a certain objective function. For the purposes of strategic port capacity planning, BAP must be solved many times in extensive simulations, needed to account for ship traffic and handling times uncertainties, and alternative terminal designs. The algorithm selection problem (ASP) consists in selecting algorithms with the best performance for a considered application. We propose a new method of selecting a portfolio of algorithms that will solve the considered BAP instances and return good solutions. The portfolio selection is based on the performance on the training instances. The performance is measured by the runtime and solution quality. In order to select the portfolio, a linear program minimizing the solution quality loss, subject to overall runtime limit is used. Thus, the portfolio evolves with the runtime limit, which is a key parameter in designing the port capacity simulations. For the training and validating datasets, random instances and real ship traffic logs are used. A portfolio of heuristics is developed which can be used for solving large instances of BAP, emerging when time horizons of months or years are considered. The evolution of the algorithm portfolios under changing runtime limits is studied. The portfolio abilities to solve new instances are assessed. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Scheduling Heuristics algorithm selection problem Berth allocation problem Quality-runtime trade-off algorithm portfolios

来源：评论

学校读者我要写书评

暂无评论

Automated Scheduling algorithm selection and Chunk Parameter Calculation in OpenMP

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2022年第12期33卷 4383-4394页

作者： Mohammed, Ali Korndoerfer, Jonas H. Mueller Eleliemy, Ahmed Ciorba, Florina M. HPEs HPC AI EMEA Res Lab ERL CH-4051 Basel Switzerland Univ Basel Dept Math & Comp Sci CH-4051 Basel Switzerland

Increasing node and cores-per-node counts in supercomputers render scheduling and load balancing critical for exploiting parallelism. OpenMP applications can achieve high performance via careful selection of scheduling kind and chunk parameters on a per-loop, per-application, and per-system basis from a portfolio of advanced scheduling algorithms (Korndorfer etal., 2022). This selection approach is time-consuming, challenging, and may need to change during execution. We propose Auto4OMP, a novel approach for automated load balancing of OpenMP applications. With Auto4OMe we introduce three scheduling algorithm selection methods and an expert-defined chunk parameter for OpenMP's schedule clause's kind and chunk, respectively. Auto4OMP extends the OpenMP schedule (auto) and chunk parameter implementation in LLVM's OpenMP runtime library to automatically select a scheduling algorithm and calculate a chunk parameter during execution. Loop characteristics are inferred in Auto4OMP from the loop execution over the application's time-steps. The experiments performed in this work show that Auto4OMP improves applications performance by up to 11% compared to LLVM's schedule (auto) implementation and outperforms manual selection. Auto4OMP improves MPI+OpenMP applications performance by explicitly minimizing thread- and implicitly reducing process-load imbalance.

关键词： Automatic selection algorithm selection problem dynamic load balancing self-scheduling runtime library OpenMP multithreaded programming shared-memory systems

来源：评论

学校读者我要写书评

暂无评论

Constructing a Meta-Learner for Unsupervised Anomaly Detection

引用

IEEE ACCESS 2023年 11卷 45815-45825页

作者： Gutowska, Malgorzata Little, Suzanne Mccarren, Andrew Dublin City Univ Sch Comp Dublin 9 Ireland

Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the diversity of problems, no single algorithm has been found to be superior for all AD tasks. Choosing an algorithm, otherwise known as the algorithm selection problem (ASP), has been extensively examined in supervised classification problems, through the use of meta-learning and AutoML, however, it has received little attention in unsupervised AD tasks. This research proposes a new meta-learning approach that identifies an appropriate unsupervised AD algorithm given a set of meta-features generated from the unlabelled input dataset. The performance of the proposed meta-learner is superior to the current state of the art solution. In addition, a mixed model statistical analysis has been conducted to examine the impact of the meta-learner components: the meta-model, meta-features, and the base set of AD algorithms, on the overall performance of the meta-learner. The analysis was conducted using more than 10,000 datasets, which is significantly larger than previous studies. Results indicate that a relatively small number of meta-features can be used to identify an appropriate AD algorithm, but the choice of a meta-model in the meta-learner has a considerable impact.

关键词： Meta-learning Classification algorithms Anomaly detection Machine learning algorithms Measurement Benchmark testing Unsupervised learning unsupervised anomaly detection algorithm selection problem model selection meta-learning meta-features

来源：评论

学校读者我要写书评

暂无评论

Stochastic local search and parameters recommendation: a case study on flowshop problems

引用

INTERNATIONAL TRANSACTIONS IN OPERATIONAL RESEARCH 2023年第2期30卷 774-799页

作者： Pavelski, Lucas M. Delgado, Myriam Kessaci, Marie-Eleonore Freitas, Alex A. Univ Tecnol Fed Parana CPGEI Av Sete Setembro Curitiba Parana Brazil Univ Lille Cent Lille CNRS UMR 9189CRIStAL F-59000 Lille France Univ Kent Sch Comp Canterbury Kent England

The algorithm selection problem (ASP) considers the use of previous knowledge regarding problem features and algorithm performance to recommend the best strategy to solve a previously unseen problem. In the application context, the usual ASP for optimization considers recommending the best heuristics, whenever it faces a new similar problem instance, also known as the Per-Instance ASP. Although ASP for heuristic recommendation is not new, selecting heuristics and also their parameters, or the Per-instance algorithm Configuration problem, is still considered a challenging task. This paper investigates the use of meta-learning to recommend six different stochastic local searches and their parameters to solve several instances of permutation flowshop problems. The proposed approach uses several problem features, including fitness landscape metrics, builds the performance database using irace, and trains different multi-label recommendation models on a data set with more than 6000 flowshop problem instances. Experiments show that decision tree-based machine learning models achieve good performance, and the quality of the recommendations is capable of outperforming the state-of-the-art algorithm with tuned configuration.

关键词： algorithm selection problem automatic algorithm configuration flowshop stochastic local search

来源：评论

学校读者我要写书评

暂无评论

Practical performance models of algorithms in evolutionary program induction and other domains

引用

ARTIFICIAL INTELLIGENCE 2010年第15期174卷 1254-1276页

作者： Graff, Mario Poli, Riccardo Univ Essex Sch Comp Sci & Elect Engn Colchester CO4 3SQ Essex England

Evolutionary computation techniques have seen a considerable popularity as problem solving and optimisation tools in recent years. Theoreticians have developed a variety of both exact and approximate models for evolutionary program induction algorithms. However, these models are often criticised for being only applicable to simplistic problems or algorithms with unrealistic parameters. In this paper, we start rectifying this situation in relation to what matters the most to practitioners and users of program induction systems: performance. That is, we introduce a simple and practical model for the performance of program-induction algorithms. To test our approach, we consider two important classes of problems - symbolic regression and Boolean function induction - and we model different versions of genetic programming, gene expression programming and stochastic iterated hill climbing in program space. We illustrate the generality of our technique by also accurately modelling the performance of a training algorithm for artificial neural networks and two heuristics for the off-line bin packing problem. We show that our models, besides performing accurate predictions, can help in the analysis and comparison of different algorithms and/or algorithms with different parameters setting. We illustrate this via the automatic construction of a taxonomy for the stochastic program-induction algorithms considered in this study. The taxonomy reveals important features of these algorithms from the performance point of view, which are not detected by ordinary experimentation. (c) 2010 Elsevier B.V. All rights reserved.

关键词： Evolution algorithms Program induction Performance prediction algorithm taxonomies algorithm selection problem

来源：评论

学校读者我要写书评

暂无评论

Meta-learning how to forecast time series

引用

JOURNAL OF FORECASTING 2023年第6期42卷 1476-1501页

作者： Talagala, Thiyanga S. S. Hyndman, Rob J. J. Athanasopoulos, George Univ Sri Jayewardenepura Fac Appl Sci Dept Stat Sri Jayewardenepura Kotte Sri Lanka Monash Univ Dept Econometr & Business Stat Melbourne Vic Australia Univ Sri Jayewardenepura Fac Appl Sci Dept Stat Sri Jayewardenepura Kotte Sri Lanka

Features of time series are useful in identifying suitable models for forecasting. We present a general framework, labelled Feature-based FORecast Model selection (FFORMS), which selects forecast models based on features calculated from each time series. The FFORMS framework builds a mapping that relates the features of a time series to the "best" forecast model using a classification algorithm such as a random forest. The framework is evaluated using time series from the M-forecasting competitions and is shown to yield forecasts that are almost as accurate as state-of-the-art methods but are much faster to compute. We use model-agnostic machine learning interpretability methods to explore the results and to study what types of time series are best suited to each forecasting model.

关键词： algorithm selection problem black-box models machine learning interpretability random forest visualization

来源：评论

学校读者我要写书评

暂无评论

MPI collective algorithm selection and quadtree encoding

MPI collective algorithm selection and quadtree encoding

引用

13th EuroPVM/MPI Conference

作者： Pjesivac-Grbovic, Jelena Bosilca, George Fagg, Graham E. Angskun, Thara Dongarra, Jack J. Univ Tennessee Dept Comp Sci Innovat Comp Lab Knoxville TN 37996 USA

ISBN: (纸本)354039110X

We explore the applicability of the quadtree encoding method to the run-time MPI collective algorithm selection problem. Measured algorithm performance data was used to construct quadtrees with different properties. The quality and performance of generated decision functions and in-memory decision systems were evaluated. Experimental data shows that in some cases, a decision function based on a quadtree structure with a mean depth of three, incurs on average as little as a 5% performance penalty. In all cases, experimental data can be fully represented with a quadtree containing a maximum of six levels. Our results indicate that quadtrees may be a feasible choice for both processing of the performance data and automatic decision function generation. (C) 2007 Elsevier B.V. All rights reserved.

关键词： MPI collective operations performance optimization algorithm selection problem quadtree encoding performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Sampling Methods for Selecting Datasets in Active Meta-Learning

Uncertainty Sampling Methods for Selecting Datasets in Activ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Prudencio, Ricardo B. C. Soares, Carlos Ludermir, Teresa B. Univ Fed Pernambuco Ctr Informat BR-50732970 Recife PE Brazil Univ Porto Fac Econ LIAAD INESC Porto L A Oporto 4050190 Portugal

ISBN: (纸本)9781424496365

Several meta-learning approaches have been developed for the problem of algorithm selection. In this context, it is of central importance to collect a sufficient number of datasets to be used as meta-examples in order to provide reliable results. Recently, some proposals to generate datasets have addressed this issue with successful results. These proposals include datasetoids, which is a simple manipulation method to obtain new datasets from existing ones. However, the increase in the number of datasets raises another issue: in order to generate meta-examples for training, it is necessary to estimate the performance of the algorithms on the datasets. This typically requires running all candidate algorithms on all datasets, which is computationally very expensive. In a recent paper, active meta-learning has been used to address this problem. An uncertainty sampling method for the k-NN algorithm using a least confidence score based on a distance measure was employed. Here we extend that work, namely by investigating three hypotheses: 1) is there advantage in using a frequency-based least confidence score over the distance-based score? 2) given that the meta-learning problem used has three classes, is it better to use a margin-based score? and 3) given that datasetoids are expected to contain some noise, are better results achieved by starting the search with all datasets already labeled? Some of the results obtained are unexpected and should be further analyzed. However, they confirm that active meta-learning can significantly reduce the computational cost of meta-learning with potential gains in accuracy.

关键词： Computational efficiency Entropy Machine learning Machine learning algorithms Sampling methods Training Uncertainty active meta-learning algorithm selection problem data analysis dataset selection datasetoids distance measure frequency-based least confidence score k-NN algorithm learning (artificial intelligence) margin-based score sampling methods uncertainty sampling method

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Predicting Solutions in Streaming Optimisation Domains

A Deep Learning Approach to Predicting Solutions in Streamin...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Alissa, Mohamad Sim, Kevin Hart, Emma Napier Univ Sch Comp Edinburgh Midlothian Scotland

ISBN: (纸本)9781450371285

In the field of combinatorial optimisation, per-instance algorithm selection still remains a challenging problem, particularly with respect to streaming problems such as packing or scheduling. Typical approaches involve training a model to predict the best algorithm based on features extracted from the data, which is well known to be a difficult task and even more challenging with streaming data. We propose a radical approach that bypasses algorithm-selection altogether by training a Deep-Learning model using solutions obtained from a set of heuristic algorithms to directly predict a solution from the instance-data. To validate the concept, we conduct experiments using a packing problem in which items arrive in batches. Experiments conducted on six large datasets using batches of varying size show the model is able to accurately predict solutions, particularly with small batch sizes, and surprisingly in a small number of cases produces better solutions than any of the algorithms used to train the model.

关键词： algorithm selection problem Deep Learning Bin-packing

来源：评论

学校读者我要写书评

暂无评论

A framework to select heuristics for the rectangular two-dimensional strip packing problem

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第PartC期213卷

作者： Neuenfeldt Jr, Alvaro Siluk, Julio Francescatto, Matheus Stieler, Gabriel Disconzi, David Univ Fed Santa Maria Innovat & Competitiveness Grp Santa Maria Brazil

Defining the algorithm capable of best fit the characteristics observed for a problem is a complex task in the context of combinatorial optimization problems. As a decision-making process, one of the most practical and useful ways to treat and solve algorithm selection problems is using supervised machine learning techniques to search for patterns between explanatory variables characteristics of the problem and the algorithms available to be selected. The present article deals with the development of a framework to fit classification models based on supervised machine learning techniques to select improvement heuristics for the rectangular 2D strip packing problem (2D-SPP) with 90-degrees rotation. Classification models were fitted to predict the best improvement heuristic for constructive heuristics bottom-left, bottom-left-fill, best-fit, best-fit with bottom-left-fill, fast -heu-ristic, and fast-heuristic with bottom-left-fill, using 19 features provided by problem characteristics. A total of 15,666 benchmark problem instances from the literature were used to represent the rectangular 2D-SPP char-acteristics variations found in real-world applications to train and test the fitted classification models. The framework proved to be consistent to predict improvement heuristics with acceptable accuracy, being able to be applied for the prediction of other cutting and packing problems algorithms.

关键词： Strip packing problems Cutting and packing problems algorithm selection problem Heuristics Classification analysis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：