检索结果-内蒙古大学图书馆

作者： Marc W. Chalé Air Force Institute of Technology

学位级别：硕士

A holistic approach to the algorithm selection problem is presented. The “algorithm selection framework" uses a combination of user input and meta-data to streamline the algorithm selection for any data analysis task. The framework removes the conjecture of the common trial and error strategy and generates a preference ranked list of recommended analysis techniques. The framework is performed on nine analysis problems. Each of the recommended analysis techniques are implemented on the corresponding data sets. algorithm performance is assessed using the primary metric of recall and the secondary metric of run time. In six of the problems, the recall of the top ranked recommendation is considered excellent with at least 95 percent of the best observed recall; the average of this metric is 79 percent due to two poorly performing recommendations. The top recommendation is Pareto efficient for three of the problems. The framework measures well against an a-priori set of criteria. The framework provides value by filtering the candidate of analytic techniques and, often, selecting a high performing technique as the top ranked recommendation. The user input and meta-data used by the framework contain information with high potential for effective algorithm selection. Future work should optimize the recommendation logic and expand the scope of techniques for other types of analysis problems. Further, the results of this proposed study should be leveraged in order to better understand the behavior of meta-learning models.

关键词： meta-learning machine learning algorithm selection data analysis artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Optimization of heuristic search using recursive algorithm selection and reinforcement learning

引用

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2010年第1-2期60卷 119-151页

作者： Vasilikos, Vasileios Lagoudakis, Michail G. Tech Univ Crete Dept Elect & Comp Engn Intelligent Syst Lab Khania 73100 Crete Greece

The traditional approach to computational problem solving is to use one of the available algorithms to obtain solutions for all given instances of a problem. However, typically not all instances are the same, nor a single algorithm performs best on all instances. Our work investigates a more sophisticated approach to problem solving, called Recursive algorithm selection, whereby several algorithms for a problem (including some recursive ones) are available to an agent that makes an informed decision on which algorithm to select for handling each sub-instance of a problem at each recursive call made while solving an instance. Reinforcement learning methods are used for learning decision policies that optimize any given performance criterion (time, memory, or a combination thereof) from actual execution and profiling experience. This paper focuses on the well-known problem of state-space heuristic search and combines the A* and RBFS algorithms to yield a hybrid search algorithm, whose decision policy is learned using the Least-Squares Policy Iteration (LSPI) algorithm. Our benchmark problem domain involves shortest path finding problems in a real-world dataset encoding the entire street network of the District of Columbia (DC), USA. The derived hybrid algorithm exhibits better performance results than the individual algorithms in the majority of cases according to a variety of performance criteria balancing time and memory. It is noted that the proposed methodology is generic, can be applied to a variety of other problems, and requires no prior knowledge about the individual algorithms used or the properties of the underlying problem instances being solved.

关键词： Heuristic search algorithm selection Reinforcement learning Software optimization Hybrid algorithms

来源：评论

学校读者我要写书评

暂无评论

Data-driven algorithm selection and tuning in optimization and signal processing

引用

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2021年第7期89卷 711-735页

作者： De Loera, Jesus A. Haddock, Jamie Ma, Anna Needell, Deanna Univ Calif Davis Davis CA 95616 USA Univ Calif Los Angeles Los Angeles CA 90095 USA Univ Calif Irvine Irvine CA USA

Machine learning algorithms typically rely on optimization subroutines and are well known to provide very effective outcomes for many types of problems. Here, we flip the reliance and ask the reverse question: can machine learning algorithms lead to more effective outcomes for optimization problems? Our goal is to train machine learning methods to automatically improve the performance of optimization and signal processing algorithms. As a proof of concept, we use our approach to improve two popular data processing subroutines in data science: stochastic gradient descent and greedy methods in compressed sensing. We provide experimental results that demonstrate the answer is "yes", machine learning algorithms do lead to more effective outcomes for optimization problems, and show the future potential for this research direction. In addition to our experimental work, we prove relevant Probably Approximately Correct (PAC) learning theorems for our problems of interest. More precisely, we show that there exists a learning algorithm that, with high probability, will select the algorithm that optimizes the average performance on an input set of problem instances with a given distribution.

关键词： Automated machine learning Compressed sensing Neural networks algorithm selection Hyperparameter tuning

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

Speeding up algorithm selection using average ranking and active testing by introducing runtime

引用

MACHINE LEARNING 2018年第1期107卷 79-108页

作者： Abdulrahman, Salisu Mamman Brazdil, Pavel van Rijn, Jan N. Vanschoren, Joaquin Kano Univ Sci & Technol Wudil Kano State Nigeria INESC TEC LIAAD Rua Dr Roberto Frias P-4200465 Oporto Portugal Univ Porto Fac Econ Rua Dr Roberto Frias P-4200465 Oporto Portugal Univ Freiburg Freiburg Germany Leiden Univ Leiden Inst Adv Comp Sci Leiden Netherlands Eindhoven Univ Technol Eindhoven Netherlands

algorithm selection methods can be speeded-up substantially by incorporating multi-objective measures that give preference to algorithms that are both promising and fast to evaluate. In this paper, we introduce such a measure, A3R, and incorporate it into two algorithm selection techniques: average ranking and active testing. Average ranking combines algorithm rankings observed on prior datasets to identify the best algorithms for a new dataset. The aim of the second method is to iteratively select algorithms to be tested on the new dataset, learning from each new evaluation to intelligently select the next best candidate. We show how both methods can be upgraded to incorporate a multi-objective measure A3R that combines accuracy and runtime. It is necessary to establish the correct balance between accuracy and runtime, as otherwise time will be wasted by conducting less informative tests. The correct balance can be set by an appropriate parameter setting within function A3R that trades off accuracy and runtime. Our results demonstrate that the upgraded versions of Average Ranking and Active Testing lead to much better mean interval loss values than their accuracy-based counterparts.

关键词： algorithm selection Meta-learning Ranking of algorithms Average ranking Active testing Loss curves Mean interval loss

来源：评论

学校读者我要写书评

暂无评论

Fast algorithm selection Using Learning Curves 14th

Fast Algorithm Selection Using Learning Curves

引用

14th International Symposium on Intelligent Data Analysis (IDA)

作者： van Rijn, Jan N. Abdulrahman, Salisu Mamman Brazdil, Pavel Vanschoren, Joaquin Leiden Univ Leiden Netherlands Univ Porto Oporto Portugal Eindhoven Univ Technol Eindhoven Netherlands

ISBN: (纸本)9783319244655

One of the challenges in Machine Learning to find a classifier and parameter settings that work well on a given dataset. Evaluating all possible combinations typically takes too much time, hence many solutions have been proposed that attempt to predict which classifiers are most promising to try. As the first recommended classifier is not always the correct choice, multiple recommendations should be made, making this a ranking problem rather than a classification problem. Even though this is a well studied problem, there is currently no good way of evaluating such rankings. We advocate the use of Loss Time Curves, as used in the optimization literature. These visualize the amount of budget (time) needed to converge to a acceptable solution. We also investigate a method that utilizes the measured performances of classifiers on small samples of data to make such recommendation, and adapt it so that it works well in Loss Time space. Experimental results show that this method converges extremely fast to an acceptable solution.

关键词： algorithm selection Meta-learning Subsampling

来源：评论

学校读者我要写书评

暂无评论

Run2Survive: A Decision-theoretic Approach to algorithm selection based on Survival Analysis 12

Run2Survive: A Decision-theoretic Approach to Algorithm Sele...

引用

Asian Conference on Machine Learning

作者： Tornede, Alexander Wever, Marcel Werner, Stefan Mohr, Felix Huellermeier, Eyke Paderborn Univ Heinz Nixdorf Inst Paderborn Germany Paderborn Univ Dept Comp Sci Paderborn Germany Univ La Sabana Chia Cundinamarca Colombia

algorithm selection (AS) deals with the automatic selection of an algorithm from a fixed set of candidate algorithms most suitable for a specific instance of an algorithmic problem class, where "suitability" often refers to an algorithm's runtime. Due to possibly extremely long runtimes of candidate algorithms, training data for algorithm selection models is usually generated under time constraints in the sense that not all algorithms are run to completion on all instances. Thus, training data usually comprises censored information, as the true runtime of algorithms timed out remains unknown. However, many standard AS approaches are not able to handle such information in a proper way. On the other side, survival analysis (SA) naturally supports censored data and offers appropriate ways to use such data for learning distributional models of algorithm runtime, as we demonstrate in this work. We leverage such models as a basis of a sophisticated decision-theoretic approach to algorithm selection, which we dub Run2Survive. Moreover, taking advantage of a framework of this kind, we advocate a risk-averse approach to algorithm selection, in which the avoidance of a timeout is given high priority. In an extensive experimental study with the standard benchmark ASlib, our approach is shown to be highly competitive and in many cases even superior to state-of-the-art AS approaches.

关键词： algorithm selection survival analysis risk-aversion surrogate loss

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

ASAP: An Automatic algorithm selection Approach for Planning

ASAP: An Automatic Algorithm Selection Approach for Planning

引用

25th Annual IEEE International Conference on Tools with Artificial Intelligence (ICTAI)

作者： Vallati, Mauro Chrpa, Lukas Kitchin, Diane Univ Huddersfield Sch Comp & Engn PK Res Grp Huddersfield HD1 3DH W Yorkshire England

Despite the advances made in the last decade in automated planning, no planner outperforms all the others in every known benchmark domain. This observation motivates the idea of selecting different planning algorithms for different domains. Moreover, the planners' performances are affected by the structure of the search space, which depends on the encoding of the considered domain. In many domains, the performance of a planner can be improved by exploiting additional knowledge, for instance, in the form of macro-operators or entanglements. In this paper we propose ASAP, an automatic algorithm selection Approach for Planning that (i) for a given domain initially learns additional knowledge, in the form of macro operators and entanglements, which is used for creating different encodings of the given planning domain and problems, and (ii) explores the 2 dimensional space of available algorithms, defined as encodings-planners couples, and then (iii) selects the most promising algorithm for optimising either the runtimes or the quality of the solution plans.

关键词： Automated planning algorithm selection learning for planning

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

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：