检索结果-内蒙古大学图书馆

The algorithm selection competitions 2015 and 2017

ARTIFICIAL INTELLIGENCE 2019年 272卷 86-100页

作者： Lindauer, Marius van Rijn, Jan N. Kotthoff, Lars Univ Freiburg Freiburg Germany Columbia Univ New York NY 10027 USA Univ Wyoming Laramie WY 82071 USA

The algorithm selection problem is to choose the most suitable algorithm for solving a given problem instance. It leverages the complementarity between different approaches that is present in many areas of Al. We report on the state of the art in algorithm selection, as defined by the algorithm selection competitions in 2015 and 2017. The results of these competitions show how the state of the art improved over the years. We show that although performance in some cases is very good, there is still room for improvement in other cases. Finally, we provide insights into why some scenarios are hard, and pose challenges to the community on how to advance the current state of the art. (C) 2018 Elsevier B.V. All rights reserved.

关键词： algorithm selection Meta-Learning Competition Analysis

来源：评论

学校读者我要写书评

暂无评论

Automating algorithm selection: Checking for matrix properties that can simplify computations

引用

JOURNAL OF SYMBOLIC COMPUTATION 2019年 94卷 1-29页

作者： Eberly, Wayne Univ Calgary Dept Comp Sci Calgary AB Canada

Initial findings in a study of the automatic selection of algorithms for matrix computations are reported. These include the presentation and analysis of algorithms for the detection and certification of matrix properties allowing the reliable use of a variety of special-purpose algorithms for sparse and structured matrix computations. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： algorithm selection Detection and certification of matrix properties Sparse and structured matrix computations Computations over finite fields

来源：评论

学校读者我要写书评

暂无评论

To quantum or not to quantum: towards algorithm selection in near-term quantum optimization

引用

QUANTUM SCIENCE AND TECHNOLOGY 2020年第4期5卷

作者： Moussa, Charles Calandra, Henri Dunjko, Vedran Leiden Univ LIACS Niels Bohrweg 1 NL-2333 CA Leiden Netherlands TOTAL SA Courbevoie France

The Quantum approximate optimization algorithm (QAOA) constitutes one of the often mentioned candidates expected to yield a quantum boost in the era of near-term quantum computing. In practice, quantum optimization will have to compete with cheaper classical heuristic methods, which have the advantage of decades of empirical domain-specific enhancements. Consequently, to achieve optimal performance we will face the issue of algorithm selection, well-studied in practical computing. Here we introduce this problem to the quantum optimization domain. Specifically, we study the problem of detecting those problem instances of where QAOA is most likely to yield an advantage over a conventional algorithm. As our case study, we compare QAOA against the well-understood approximation algorithm of Goemans and Williamson on the Max-Cut problem. As exactly predicting the performance of algorithms can be intractable, we utilize machine learning (ML) to identify when to resort to the quantum algorithm. We achieve cross-validated accuracy well over 96%, which would yield a substantial practical advantage. In the process, we highlight a number of features of instances rendering them better suited for QAOA. While we work with simulated idealised algorithms, the flexibility of ML methods we employed provides confidence that our methods will be equally applicable to broader classes of classical heuristics, and to QAOA running on real-world noisy devices.

关键词： algorithm selection quantum algorithms combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Limitations of benchmark sets and landscape features for algorithm selection and performance prediction 19

Limitations of benchmark sets and landscape features for alg...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Lacroix, Benjamin McCall, John Robert Gordon Univ Aberdeen Scotland

ISBN: (纸本)9781450367486

Benchmark sets and landscape features are used to test algorithms and to train models to perform algorithm selection or configuration. These approaches are based on the assumption that algorithms have similar performances on problems with similar feature sets. In this paper, we test different configurations of differential evolution (DE) against the BBOB set. We then use the landscape features of those problems and a case base reasoning approach for DE configuration selection. We show that, although this method obtains good results for BBOB problems, it fails to select the best configurations when facing a new set of optimisation problems with a distinct array of landscape features. This demonstrates the limitations of the BBOB set for algorithm selection. Moreover, by examination of the relationship between features and algorithm performance, we show that there is no correlation between the feature space and the performance space. We conclude by identifying some important open questions raised by this work.

关键词： Continuous optimisation numerical optimisation benchmark functions algorithm selection exploratory landscape analysis

来源：评论

学校读者我要写书评

暂无评论

Line selection and algorithm selection for Transmission Switching by Machine Learning Methods

Line Selection and Algorithm Selection for Transmission Swit...

引用

IEEE Milan PowerTech Conference

作者： Yang, Zhu Oren, Shmuel Univ Calif Berkeley Dept Ind Engn & Operat Res Berkeley CA 94720 USA

ISBN: (纸本)9781538647226

Since the initial proposal of the Optimal Transmission Switching problem, a mixed integer program and different heuristics have been presented to achieve considerable cost reduction within a practical time frame. This paper proposes two machine learning based methods to further reduce the computation time as well as cutting down the generation cost. The first method is to apply machine learning algorithms to prioritize the possible line switching actions. The second method is to use machine learning to develop effective algorithm selectors among transmission switching algorithms suggested in the literature. The proposed methods are tested on IEEE 118-bus test case and FERC 13867-bus test case. The results demonstrated that both line selection and algorithm selection offer performance benefits over using the single transmission switching algorithm in the previous literature.

关键词： Transmission switching machine learning algorithm selection

来源：评论

学校读者我要写书评

暂无评论

Simplifying the algorithm selection Using Reduction of Rankings of Classification algorithms 19

Simplifying the Algorithm Selection Using Reduction of Ranki...

引用

8th International Conference on Software and Computer Applications (ICSCA)

作者： Abdulrahman, Salisu Mamman Brazdil, Pavel Zainon, Wan Mohd Nazmee Wan Adamu, Alhassan Kano Univ Sci & Technol Wudil Kano Nigeria Univ Porto Fac Econ LIAAD INESCTEC Porto Portugal USM Sch Comp Sci George Town Malaysia

ISBN: (纸本)9781450365734

The average ranking method (AR) is one of the simplest and effective algorithms selection methods. This method uses metadata in the form of test results of a given set of algorithms on a given set of datasets and calculates an average rank for each algorithm. The ranks are used to construct the average ranking. In this paper we investigate the problem of how the rankings can be reduced by removing non-competitive and redundant algorithms, thereby reducing the number of tests a user needs to conduct on a new dataset to identify the most suitable algorithm. The method proposed involves two phases. In the first one, the aim is to identify the most competitive algorithms for each dataset used in the past. This is done with the recourse to a statistical test. The second phase involves a covering method whose aim is to reduce the algorithms by eliminating redundant variants. The proposed method differs from one earlier proposal in various aspects. One important one is that it takes both accuracy and time into consideration. The proposed method was compared to the baseline strategy which consists of executing all algorithms from the ranking. It is shown that the proposed method leads to much better performance than the baseline.

关键词： Meta-learning algorithm selection Average Ranking Eliminating non-competitive and redundant algorithms

来源：评论

学校读者我要写书评

暂无评论

Graph Convolutional Network Based Generative Adversarial Networks for the algorithm selection Problem in Classification

Graph Convolutional Network Based Generative Adversarial Net...

引用

作者： Gleb Drozdov Alexey Zabashta Andrey Filchenkov ITMO University

In this work,we address the algorithm selection problem for classification via meta-learning and generative adversarial *** focus on the dataset representation *** matrix representation of classification dataset is not sensitive to swapping any two rows or any two *** suggest a special method to reduce a dataset to a unified *** allows to apply generative adversarial networks to classification dataset *** this setting,a generator generates new classification datasets in a matrix form,while a conditional discriminator is trying to predict for a dataset and an algorithm if the dataset is real and the algorithm would show the best performance on this *** also suggest a graph convolutional network as a discriminator that is capable to work with such forms,which encode a dataset as a weighted graph with nodes representing objects.

关键词： Machine learning Meta-learning Generative adversarial nets Dataset synthesis Graph convolutional network Dataset representation algorithm selection

来源：评论

学校读者我要写书评

暂无评论

algorithm selection for Classification Problems via Cluster-based Meta-features

Algorithm Selection for Classification Problems via Cluster-...

引用

IEEE International Conference on Big Data (Big Data)

作者： Ler, Daren Teng, Hongyu He, Yu Gidijala, Rahul Minist Educ Singapore Singapore Natl Jr Coll Singapore Singapore

ISBN: (纸本)9781538650356

Meta-features describe the characteristics of the datasets to facilitate algorithm selection. This paper proposes a new set of meta-features based on clustering the instances within datasets. We propose the use of a greedy clustering algorithm, and evaluate the meta-features generated based on the learning curves produced by the Random Forest algorithm. We also compared the utility of the proposed meta-features against preexisting meta-features described in the literature, and evaluated the applicability of these meta-features over a sample of UCI datasets. Our results show that these meta-features do indeed improve the performance when applied to the algorithm selection task.

关键词： meta-learning algorithm selection cluster-based meta-features

来源：评论

学校读者我要写书评

暂无评论

algorithm selection on Generalized Quadratic Assignment Problem Landscapes 18

Algorithm Selection on Generalized Quadratic Assignment Prob...

引用

Genetic and Evolutionary Computation Conference (GECCO)

作者： Beham, Andreas Wagner, Stefan Affenzeller, Michael FH Upper Austria Res Grp HEAL Hagenberg Austria Johannes Kepler Univ Linz Inst Formal Models & Verificat Linz Austria

ISBN: (纸本)9781450356183

algorithm selection is useful in decision situations where among many alternative algorithm instances one has to be chosen. This is often the case in heuristic optimization and is detailed by the well-known no-free-lunch (NFL) theorem. A consequence of the NFL is that a heuristic algorithm may only gain a performance improvement in a subset of the problems. With the present study we aim to identify correlations between observed differences in performance and problem characteristics obtained from statistical analysis of the problem instance and from fitness landscape analysis (FLA). Finally, we evaluate the performance of a recommendation algorithm that uses this information to make an informed choice for a certain algorithm instance.

关键词： fitness landscapes algorithm selection assignment problems

来源：评论

学校读者我要写书评

暂无评论

Metalearning and Recommender Systems: A literature review and empirical study on the algorithm selection problem for Collaborative Filtering

引用

INFORMATION SCIENCES 2018年 423卷 128-144页

作者： Cunha, Tiago Soares, Carlos de Carvalho, Andre C. P. L. F. Univ Porto Fac Engn Oporto Portugal Univ Sao Paulo ICMC Sao Carlos SP Brazil

The problem of information overload motivated the appearance of Recommender Systems. From the several open problems in this area, the decision of which is the best recommendation algorithm for a specific problem is one of the most important and less studied. The current trend to solve this problem is the experimental evaluation of several recommendation algorithms in a handful of datasets. However, these studies require an extensive amount of computational resources, particularly processing time. To avoid these drawbacks, researchers have investigated the use of Metalearning to select the best recommendation algorithms in different scopes. Such studies allow to understand the relationships between data characteristics and the relative performance of recommendation algorithms, which can be used to select the best algorithm(s) for a new problem. The contributions of this study are two-fold: 1) to identify and discuss the key concepts of algorithm selection for recommendation algorithms via a systematic literature review and 2) to perform an experimental study on the Metalearning approaches reviewed in order to identify the most promising concepts for automatic selection of recommendation algorithms. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Metalearning algorithm selection Recommendation system Collaborative Filtering

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：