检索结果-内蒙古大学图书馆

ARCS 2016;29th International Conference on Architecture of Computing Systems

作者： Romeo Shuka Sebastian Niemann Juergen Brehm Christian Mueller-Schloer Institute of Systems Engineering System and Computer Architecture Leibniz Universitat Hannover

The adaptation of sequential algorithms for High Performance Computing (HPC) systems is determined by a tradeoff between algorithmic effectiveness (software) and communication frequency (hardware) of the parallel implementation (efficiency). To get a better understanding of the correlation, we define simple models for both, software and hardware, in order to dynamically find the best mapping parameters for the execution of the algorithm on the parallel system. For the evaluation of our method we look at population-based algorithms like the Particle Swarm optimization Algorithm (PSO) for the solution of optimization problems. Different goals like best quality of the solution of the optimization problem for a given execution time or best execution time to find the optimum are defined by the user. Our method enables us to find the best parameters for the mapping which then results in an efficient and effective parallel implementation to achieve the user-defined goals on a High Performance Computing Cluster (HPCC).

关键词： High Performance Computing optimization algorithms Particle Swarm optimization Particle swarm optimization High Performance Computing optimization algorithms algorithms execution time parallel system Computer hardware Parallel Lines

来源：评论

学校读者我要写书评

暂无评论

An Optimal Algorithm for Stochastic Matroid Bandit optimization 16

An Optimal Algorithm for Stochastic Matroid Bandit Optimizat...

引用

International Conference on Autonomous Agents and Multiagent Systems

作者： Mohammad Sadegh Talebi Alexandre Proutiere Department of Automatic Control KTH Royal Institute of Technology

ISBN: (纸本)9781510855083

The selection of leaders in leader-follower multi-agent systems can be naturally formulated as a matroid optimization problem. In this paper, we investigate the online and stochastic version of such a problem, where in each iteration or round, we select a set of leaders and then observe a random realization of the corresponding reward, i.e., of the system performance. This problem is referred to as a stochastic matroid bandit, a variant of combinatorial multi-armed bandit problems where the underlying combinatorial structure is a matroid. We consider semi-bandit feedback and Bernoulli rewards, and derive a tight and problem-dependent lower bound on the regret of any consistent algorithm. We propose KL-OSM, a computationally efficient algorithm that exploits the matroid structure. We derive a finite-time upper bound of the regret of KL-OSM that improves the performance guarantees of existing algorithms. This upper bound actually matches our lower bound, i.e., KL-OSM is asymptotically optimal. Numerical experiments attest that KL-OSM outperforms state-of-the-art algorithms in practice, and the difference in some cases is significant.

关键词： Multi-Armed Bandits Online Learning Combinatorial optimization Matroids Regret Analysis Matroid e-learning optimization algorithms Regret composite structures Stochastic

来源：评论

学校读者我要写书评

暂无评论

Riemannian optimization with Subspace Tracking for Low-rank Recovery

Riemannian Optimization with Subspace Tracking for Low-rank ...

引用

International Joint Conference on Neural Networks

作者： Qian Li Wenjia Niu Gang Li Jianlong Tan Gang Xiong Li Guo Institute of Information Engineering Chinese Academy of Sciences School of Information Technology Deakin University

ISBN: (纸本)9781509006212

Low-rank matrix recovery (MR) has been widely used in data analysis and dimensionality reduction. As a direct heuristic to MR, convex relaxation is usually degraded by the repeated calling of singular value decomposition (SVD), especially in large-scale applications. In this paper, we propose a novel Riemannian optimization method (ROAM) for MR problem by exploiting the Riemannian geometry of the searching space. In particular, ROAM utilizes an efficient subspace tracking schema that automatically detects the unknown rank to identify the preferable geometry space. Moreover, a gradient-based optimization algorithm is proposed to obtain the latent low-rank component, which avoids the expensive full dimension of SVD. More significantly, ROAM algorithm is proved to converge under mild assumptions, which also verifies the effectiveness of ROAM. Extensive empirical results demonstrate the improved accuracy and efficiency of ROAM over convex-relaxation approaches.

关键词： Matrix Recovery Riemannian Manifold Principle Component Pursuit Matrix Completion Singular value decomposition Subspace Riemannian geometry Swine vesicular disease dimensionality reduction optimization algorithms tracking Roaming

来源：评论

学校读者我要写书评

暂无评论

Efficient Globally Convergent Stochastic optimization for Canonical Correlation Analysis 16

Efficient Globally Convergent Stochastic Optimization for Ca...

引用

Annual Conference on Neural Information Processing Systems

作者： Weiran Wang Jialei Wang Dan Garber Nathan Srebro Toyota Technological Institute at Chicago University of Chicago

ISBN: (纸本)9781510838819

We study the stochastic optimization of canonical correlation analysis (CCA), whose objective is nonconvex and does not decouple over training samples. Although several stochastic gradient based optimization algorithms have been recently proposed to solve this problem, no global convergence guarantee was provided by any of them. Inspired by the alternating least squares/power iterations formulation of CCA, and the shift-and-invert preconditioning method for PCA, we propose two globally convergent meta-algorithms for CCA, both of which transform the original problem into sequences of least squares problems that need only be solved approximately. We instantiate the meta-algorithms with state-of-the-art SGD methods and obtain time complexities that significantly improve upon that of previous work. Experimental results demonstrate their superior performance.

关键词： multivariate analysis Stochastic original problem optimization algorithms Correlation analysis principal components analysis Passive Cutaneous Anaphylaxis complexity classes

来源：评论

学校读者我要写书评

暂无评论

Distributed optimization for multiple linear systems with bounded inputs

Distributed optimization for multiple linear systems with bo...

引用

International Workshop on Variable Structure Systems, VSS

作者： Yu Zhao Yongfang Liu Guanghui Wen School of Automation Northwestern Polytechnical University Xi'an Shaanxi Department of Mathematics Southeast University Nanjing China

This paper studies the distributed optimization problem for continuous-time multi-agent systems with general linear node dynamics. The objective is to cooperatively optimize a team performance function formed by a sum of convex local objective functions. Only local interaction and gradient information of local objective functions are utilized. To achieve the cooperative goal, a new distributed optimal algorithms are designed. An edge-based nonsmooth algorithm is developed for multi-agent linear systems with stabilizable nodes and a class of convex local objective functions. Some sufficient conditions are respectively given to ensure that all agents reach a consensus value while minimizing the team performance function. Finally, numerical examples are provided to illustrate and validate the theoretical results.

关键词： Linear system Objective function Distribute Sufficient conditions Convexity Bounded optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Identification of Switched Linear Systems via Sparse optimization

引用

IFAC-PapersOnLine 2015年第28期48卷 680-685页

作者： Jiang, Weisen Fang, Hai-Tao Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

This paper addresses identification problem of switched linear(SL) systems from input-output data. The main challenge is the partitions of data points correspond to different subsystems are unavailable. Inspired by compressed sensing theory, we pursue the sparsity of estimation error and propose `0-norm optimization algorithm to identify parameters. Unfortunately, the computational complexity of this approach is intractable. To overcome this difficulty, we replace `0-norm by `1-norm, which retains sparse property. We not only provide recoverable conditions for identifying SL systems via `1-norm minimization program, but also show that `1-norm estimator is robust to bounded noise. Numerical experiments are included to demonstrate the performance of our algorithms. © 2015

关键词： Linear systems Identification (control systems) 1 norm minimizations Estimation errors Identification problem Input output data Numerical experiments optimization algorithms Sparse optimizations Switched linear system

来源：评论

学校读者我要写书评

暂无评论

Scan path optimization with/without clustering for active beam delivery in charged particle therapy

引用

PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS 2015年第2期31卷 130-136页

作者： Dias, Marta F. Riboldi, Marco Seco, Joao Castelhano, Ines Pella, Andrea Mirandola, Alfredo Peralta, Luis Ciocca, Mario Orecchia, Roberto Baroni, Guido Univ Lisbon Fac Sci Dept Phys P-1749 Lisbon Portugal Lab Instrumentacao & Fis Particulas P-1749 Lisbon Portugal Politecn Milan Dipartimento Elettron Informaz & Bioingn I-20133 Milan Italy Ctr Nazl Adroterapia Oncol Bioengn Unit I-27100 Pavia Italy Harvard Univ Sch Med Massachusetts Gen Hosp Dept Radiat Oncol Boston MA 02114 USA Univ Lisbon Inst Biophys & Biomed Engn Fac Sci P-1749 Lisbon Portugal Ctr Nazl Adroterapia Oncol I-27100 Pavia Italy Ctr Nazl Adroterapia Oncol Dept Med I-27100 Pavia Italy European Inst Oncol Adv Radiotherapy Ctr Div Radiotherapy I-20141 Milan Italy Univ Milan Dept Sci & Biomed Technol I-20122 Milan Italy

Purpose: To compare different algorithms to optimize the scanning path in charged particle therapy with quasidiscrete scanning. We implemented a Hybrid Genetic Algorithm with Heuristics (HyGA) and combined it with clustering techniques. The performance was compared to Simulated Annealing (SA) and to commercially available treatment planning system (TPS). Methods: Performance and clinical implications were assessed using data from 10 patients treated at CNAO (Centro Nazionale di Adroterapia Oncologica). Clinical treatments are performed relying on beam deflection, avoiding irradiation for transitions between adjacent spots larger than 2 cm. A clustering method was implemented with HyGA (HyGA_Cl), which assumes beam deflection during transition between clusters. Clinical performance was determined as the total number of particles delivered during spot transitions and the number of particles wasted due to beam deflection. Results were compared to scan paths obtained with CNAO TPS. Results: SA and HyGA produced on average shorter paths compared to the currently available TPS. This did not result in a reduction of transit particles, due to the concomitant effect of beam deflection out of the extraction line. HyGA_Cl achieved 2% average reduction in transit particles when compared to CNAO TPS. As a drawback, wasted particles increased, due to more frequent use of beam deflection. Both the SA and HyGA algorithms reduced the number of wasted particles. Conclusion: SA and HyGA proved to be the most cost-effective methods in reducing wasted particles, with benefits in terms of shorter scan paths. A decrease in transit particles delivered with beam deflection can be achieved using HyGA_Cl. (C) 2015 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.

关键词： Scan path optimization algorithms Path length Transit particles Wasted particles

来源：评论

学校读者我要写书评

暂无评论

Canal Monitoring Algorithm

引用

JOURNAL OF IRRIGATION AND DRAINAGE ENGINEERING 2016年第3期142卷 015058-1-015058-10页

作者： Soler, Joan Gomez, Manuel Bonet, Enric Univ Republ Dept Water Gral Rivera 1350 Salto 50000 Uruguay Univ Politecn Cataluna FLUMEN Res Inst BarcelonaTech Jordi Girona 1-3 Barcelona 08034 Spain

One of the main problems in the water management of irrigation canals is the control of water distribution among users' outlets. This is because of the difficulty of measuring the removing flows correctly because they are highly variable in both time and space. To help solve this problem, a mathematical algorithm, the so-called canal monitoring algorithm, which determines the history of lateral extractions, is propounded. It uses the water depth measurements at checkpoints and the gate and other control device trajectories, which are implemented on the canal during a past period of time, and then obtains water withdrawals that happened at the outlets. The method also gives an estimation of the current state of the canal for model predictive control purposes. The algorithm solves the classical inverse problem, in which the unknowns are the parameters that define the flow rate trajectories of canal outlets, which are defined as piecewise functions of time in this paper. The algorithm is on the basis of the Gauss-Newton method and uses the complete Saint-Venant equations for the computation of the least-squared function. Numerical tests with excellent results have highlighted its computational efficiency, converging in a few iterations to the exact final results. These properties make the algorithm adequate to operate in real time. A laboratory canal test for verification shows accuracy in detecting water withdrawals at canal outlets when the Manning roughness coefficients are known. The test also reveals a functional relationship between the discharge removed and the empirical coefficients.

关键词： Free-surface flow Irrigation canal control optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Group technology-based model and cuckoo optimization algorithm for resource allocation in cloud computing

引用

IFAC-PapersOnLine 2015年第3期28卷 1140-1145页

作者： Shahdi-Pashaki, S. Teymourian, Ehsan Kayvanfar, Vahid Komaki, G.H.M. Sajadi, A. Department of Industrial Engineering Faculty of Engineering Shomal University Amol Iran Department of Industrial Engineering Mazandaran University of Science and Technology Babol Iran Department of Industrial Engineering Amirkabir University of Technology Tehran Iran Department of Electrical Engineering and Computer Science Case Western Reserve University United States

The control of operational costs is one of the main goals of resource management problem in cloud computing (CC). This paper presents a new mathematical model based on group technology (GT) to map the virtual machines (VMs) to workflows in order to control some costs (e.g. transfer costs, penalty costs and server cost) when the VMs are running. GT is a well-known manufacturing technique in industrial environments which can control some measures (e.g. part movements, resource utilization). In large size problems a cuckoo optimization algorithm (COA) is proposed. To test the effectiveness of our approaches, we first generate a set of problems randomly and then compare the model and COA with a well-known algorithm in literature called Round robin (RR). Analyzing the computational results proves that our approaches give better performance than RR. © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Cloud computing Costs Group technology Manufacture Network security optimization Resource allocation Routers Virtual machine Computational results Industrial environments Manufacturing techniques New mathematical model optimization algorithms Penalty cost Resource management problems Resource utilizations

来源：评论

学校读者我要写书评

暂无评论

Parameter optimization for Local Polynomial Approximation based Intersection Confidence Interval Filter Using Genetic Algorithm: An Application for Brain MRI Image De-Noising

引用

JOURNAL OF IMAGING 2015年第1期1卷 60-84页

作者： Dey, Nilanjan Ashour, Amira S. Beagum, Samsad Pistola, Dimitra Sifaki Gospodinov, Mitko Gospodinova, Evgeniya Peneva Tavares, Joao Manuel R. S. Techno India Coll Technol Dept Informat Technol Kolkata 700156 India Tanta Univ Fac Engn Dept Elect & Elect Commun Engn Tanta 31527 Egypt Taif Univ Coll CIT At Taif Saudi Arabia Taif Univ Coll Comp & Informat Technol Comp Sci Dept At Taif 21974 Saudi Arabia Karpagam Univ Dept Comp Sci Coimbatore 641021 Tamil Nadu India Univ Crete Dept Social Med Iraklion 60417 Greece Bulgarian Acad Sci Inst Syst Engn & Robot Sofia 1000 Bulgaria Univ Porto Fac Engn Dept Engn Mecan Inst Ciencia & Inovacao Engn Mecan & Engn Ind P-4200465 Porto Portugal

Magnetic resonance imaging (MRI) is extensively exploited for more accurate pathological changes as well as diagnosis. Conversely, MRI suffers from various shortcomings such as ambient noise from the environment, acquisition noise from the equipment, the presence of background tissue, breathing motion, body fat, etc. Consequently, noise reduction is critical as diverse types of the generated noise limit the efficiency of the medical image diagnosis. Local polynomial approximation based intersection confidence interval (LPA-ICI) filter is one of the effective de-noising filters. This filter requires an adjustment of the ICI parameters for efficient window size selection. From the wide range of ICI parametric values, finding out the best set of tunes values is itself an optimization problem. The present study proposed a novel technique for parameter optimization of LPA-ICI filter using genetic algorithm (GA) for brain MR images de-noising. The experimental results proved that the proposed method outperforms the LPA-ICI method for de-noising in terms of various performance metrics for different noise variance levels. Obtained results reports that the ICI parameter values depend on the noise variance and the concerned under test image.

关键词： magnetic resonance imaging image de-noising local polynomial approximation filter optimization algorithms genetic algorithm

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：