检索结果-内蒙古大学图书馆

A lower bound based smoothed quasi-newton algorithm for group bridge penalized regression

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION 2017年第6期46卷 4694-4707页

作者： Cao, Yongxiu Huang, Jian Jiao, Yuling Liu, Yanyan Zhongnan Univ Econ & Law Sch Math & Stat Wuhan Hubei Peoples R China Wuhan Univ Sch Math & Stat Wuhan Hubei Peoples R China Shanghai Univ Finance & Econ Sch Stat & Management Shanghai Peoples R China Univ Iowa Dept Stat & Actuarial Sci Iowa City IA 52242 USA

In this paper, we propose a lower bound based smoothed quasi-newton algorithm for computing the solution paths of the group bridge estimator in linear regression models. Our method is based on the quasi-newton algorithm with a smoothed group bridge penalty in combination with a novel data-driven thresholding rule for the regression coefficients. This rule is derived based on a necessary KKT condition of the group bridge optimization problem. It is easy to implement and can be used to eliminate groups with zero coefficients. Thus, it reduces the dimension of the optimization problem. The proposed algorithm removes the restriction of groupwise orthogonal condition needed in coordinate descent and LARS algorithms for group variable selection. Numerical results show that the proposed algorithm outperforms the coordinate descent based algorithms in both efficiency and accuracy.

关键词： Lower bound rule Group bridge Penalized least squares quasi-newton algorithm

来源：评论

学校读者我要写书评

暂无评论

A quasi-newton algorithm FOR 1ST-ORDER SADDLE-POINT LOCATION

引用

THEORETICA CHIMICA ACTA 1992年第3-4期82卷 189-205页

作者： CULOT, P DIVE, G NGUYEN, VH GHUYSEN, JM FAC UNIV NAMUR DEPT MATHB-5000 NAMURBELGIUM

A new algorithm for the location of a transition-state structure on an energy hypersurface is proposed. The method is compared to three other quasi-newton step calculations available in literature. Numerical results derived from several examples are compared to those obtained by the two algorithms implemented in the Gaussian package.

关键词： TRANSITION-STATE LOCATION quasi-newton algorithm

来源：评论

学校读者我要写书评

暂无评论

Unified 3-D structure and projection orientation refinement using quasi-newton algorithm

引用

JOURNAL OF STRUCTURAL BIOLOGY 2005年第1期149卷 53-64页

作者： Yang, C Ng, EG Penczek, PA Univ Texas Houston Med Ctr Dept Biochem & Mol Biol Houston TX 77030 USA Lawrence Berkeley Lab Computat Res Div Berkeley CA 94720 USA

We describe an algorithm for simultaneous refinement of a three-dimensional (3-D) density map and of the orientation parameters of two-dimensional (2-D) projections that are used to reconstruct this map. The application is in electron microscopy, where the 3-D structure of a protein has to be determined from a set of 2-D projections collected at random but initially unknown angles. The design of the algorithm is based on the assumption that initial low resolution approximation of the density map and reasonable guesses for orientation parameters are available. Thus, the algorithm is applicable in final stages of the structure refinement. when the quality of the results is of main concern. We define the objective function to be minimized in real space and solve the resulting nonlinear optimization problem using a quasi-newton algorithm. We calculate analytical derivatives with respect to density distribution and the finite difference approximations of derivatives with respect to orientation parameters. We demonstrate that calculation of derivatives is robust with respect to noise in the data. This is due to the fact that noise is annihilated by the back-projection operations. Our algorithm is distinguished from other orientation refinement methods (i) by the simultaneous update of the density map and orientation parameters resulting in a highly efficient computational scheme and (ii) by the high quality of the results produced by a direct minimization of the discrepancy between the 2-D data and the projected views of the reconstructed 3-D structure. We demonstrate the speed and accuracy of our method by using simulated data. (C) 2004 Elsevier Inc. All rights reserved.

关键词： 3-D structure determination electron microscopy quasi-newton algorithm

来源：评论

学校读者我要写书评

暂无评论

The Modeling of the Electric Consumption of Turkey and Estimation Using a quasi-newton algorithm up to the Year 2012

引用

ENERGY SOURCES PART B-ECONOMICS PLANNING AND POLICY 2011年第1期6卷 106-110页

作者： Demir, A. S. Taskin, H. Sakarya Univ Dept Ind Engn TR-54187 Sakarya Turkey

Determining the amount of electric consumption in a country for forthcoming years is very important for some precautions should be made. In this article, electric consumption need was modeled using electric consumption amounts for Turkey in the previous years and forecasting the demand of electricity until 2012. In the application process, the quasi-newton algorithm, one of the traditional optimization techniques, was used.

关键词： electric consumption estimation modeling optimization quasi-newton algorithm

来源：评论

学校读者我要写书评

暂无评论

PROTEIN SECONDARY STRUCTURE PREDICTION BASED ON BP NEURAL NETWORK AND quasi-newton algorithm

PROTEIN SECONDARY STRUCTURE PREDICTION BASED ON BP NEURAL NE...

引用

International Conference on Apperceiving Computing and Intelligence Analysis

作者： Wang, Jian Li, Jian-Ping Neijiang Normal Univ Sch Comp & Informat Sci Neijiang 641112 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610054 Peoples R China Logist Engn Univ Int Ctr Wavelet Anal & Appl Chongqing 400016 Peoples R China

ISBN: (纸本)9781424434275

Based on neural network, an improvement scheme that iterative matrix replace secondary derivative has been developed by introduced quasi-newton algorithm. Profile code based on probability has been used and comparison of window width and learning training has been completed. The experiment results indicate that the prediction for secondary structures of protein obtain a very good effect based on neural network and quasi-newton algorithm.

关键词： quasi-newton algorithm BP neural network protein secondary structure prediction

来源：评论

学校读者我要写书评

暂无评论

Node Localization of Wireless Sensor Networks Based on Hybrid Bat-quasi-newton algorithm

引用

INTERNATIONAL JOURNAL OF ONLINE ENGINEERING 2015年第6期11卷 38-42页

作者： Sun, Shunyuan Xu, Baoguo Jiangnan Univ Minist Educ Sch Internet Things Engn Wuxi 214122 Peoples R China Jiangnan Univ Minist Educ Key Lab Adv Proc Control Light Ind Wuxi 214122 Peoples R China

Concerning the problem that the least square method in the third stage of DV-Hop algorithm has low positioning accuracy, a localization algorithm was proposed which is the fusion of hybrid bat-quasi-newton algorithm and DV-Hop algorithm. First of all, the Bat algorithm (BA) was improved from two aspects: firstly, the random vector beta was adjusted adaptively according to bats fitness so that the pulse frequency had the adaptive ability. Secondly, bats were guided to move by the average position of all the best individuals before the current iteration so that the speed had variable performance;Then in the third stage of DV-Hop algorithm the improved bat algorithm was used to estimate node location and then quasi-newton algorithm was used to continue searching for the node location from the estimated location as the initial searching point. The simulation results show that, compared with the traditional DV-Hop algorithm and the improved algorithm of DV-Hop based on bat algorithm (BADV-Hop). Positioning precision of the proposed algorithm increases about 16.5% and 5. 18%, and the algorithm has better stability, it is suitable for high positioning precision and stability situation.

关键词： Bat algorithm (BA) DV-Hop algorithm quasi-newton algorithm Wireless Sensor Networks (WSN)

来源：评论

学校读者我要写书评

暂无评论

3-D Inversion Based on the Particle Swarm Optimization-quasi-newton Hybrid algorithm for SOTEM

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2023年 61卷

作者： Xue, Guoqiang He, Yiming Chen, Weiying Wu, Xin Song, Wanting Chinese Acad Sci Key Lab Mineral Resources Inst Geol & Geophys Beijing 100029 Peoples R China Chinese Acad Sci Innovat Acad Earth Sci Beijing 100029 Peoples R China Univ Chinese Acad Sci Coll Earth & Planetary Sci Beijing 100049 Peoples R China

The short offset transient electromagnetic method (SOTEM) has become one of the main methods for coal hydrogeology investigations and mineral explorations due to its performance advantages of high precision, large depth abilities, and high efficiency. At the present time, due to the computational complexity and memory requirements for 3-D SOTEM inversion algorithms, SOTEM data inversion is mainly based on 1-D, which has made it difficult to meet fine detection requirements under complex geological conditions. In this study, a particle swarm optimization-quasi-newton hybrid algorithm (PSO-QN) was proposed, with high precision and fast 3-D inversions of SOTEM data achieved. In addition, a flight strategy was introduced in order to ensure the global optimization of individual particles, and a weighting strategy was adopted to avoid falling into local minimums. The 3-D inversions of the SOTEM data were tested based on a variety of geoelectric models. The results showed that the dependence of the PSO-QN hybrid algorithm on the number of particle swarms had dropped to two-thirds. Furthermore, the calculation time was significantly reduced to one-third. The inversion results of the field data revealed that the proposed inversion method possessed a strong anti-noise capacity, high speed, good stability, and high resolution.

关键词： Flight strategy particle swarm optimization (PSO) algorithm quasi-newton algorithm short offset transient electromagnetic method (SOTEM) weighting strategy

来源：评论

学校读者我要写书评

暂无评论

Comparing the performance of neural networks developed by using Levenberg-Marquardt and quasi-newton with the gradient descent algorithm for modelling a multiple response grinding process

引用

EXPERT SYSTEMS WITH APPLICATIONS 2012年第3期39卷 2397-2407页

作者： Mukherjee, Indrajit Routroy, Srikanta Indian Inst Technol Shailesh J Mehta Sch Management Bombay 400076 Maharashtra India Birla Inst Technol & Sci Dept Mech Engn Pilani 333031 Rajasthan India

Monitoring and control of multiple process quality characteristics (responses) in grinding plays a critical role in precision parts manufacturing industries. Precise and accurate mathematical modelling of multiple response process behaviour holds the key for a better quality product with minimum variability in the process. Artificial neural network (ANN)-based nonlinear grinding process model using backpropagation weight adjustment algorithm (BPNN) is used extensively by researchers and practitioners. However, suitability and systematic approach to implement Levenberg-Marquardt (L-M) and Boyden, Fletcher, Gold-farb and Shanno (BFGS) update quasi-newton (Q-N) algorithm for modelling and control of grinding process is seldom explored. This paper provides L-M and BEGS algorithm-based BPNN models for grinding process, and verified their effectiveness by using a real life industrial situation. Based on the real life data, the performance of L-M and BFGS update Q-N are compared with an adaptive learning (A-L) and gradient descent algorithm-based BPNN model. The results clearly indicate that L-M and BEGS-based networks converge faster and can predict the nonlinear behaviour of multiple response grinding process with same level of accuracy as A-L based network. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： Back propagation neural network Gradient descent algorithm Levenberg-Marquardt algorithm Multiple response quasi-newton algorithm

来源：评论

学校读者我要写书评

暂无评论

A note on supply chain network equilibrium models

引用

TRANSPORTATION RESEARCH PART E-LOGISTICS AND TRANSPORTATION REVIEW 2007年第1期43卷 60-71页

作者： Meng, Qiang Huang, Yi Kai Cheu, Ruey Long Natl Univ Singapore Dept Civil Engn Singapore 117576 Singapore

This paper is concerned with the supply chain network equilibrium models proposed by Nagurney et al. [Nagurney, A., Doug, J., Zhang, D., 2002. A supply chain network equilibrium model. Transportation Research 38E, 281-303] and Dong et al. [Dong, J., Zhang, D., Nagurney, A., 2004. A supply chain network equilibrium model with random demands. European Journal of Operational Research 156, 194-212]. It demonstrates that these models possess the unconstrained continuously differentiable minimization formulations, whose any stationary point is the solution of the corresponding model. Accordingly, not only is the quasi-newton algorithm capable of finding a solution of the model, but also it can overcome the difficulty experienced by the modified projection method in choosing an appropriate predetermined step size. In addition, I I benchmark examples are employed to show the advantage of the unconstrained minimization formulation. (c) 2005 Elsevier Ltd. All rights reserved.

关键词： supply chain model network equilibrium variational inequalities nonlinear complementarity problems unconstrained minimization problems quasi-newton algorithm

来源：评论

学校读者我要写书评

暂无评论

Complex ICA by negentropy maximization

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2008年第4期19卷 596-609页

作者： Novey, Michael Adah, Tuelay Univ Maryland Baltimore Cty Dept Comp Sci & Elect Engn Baltimore MD 21250 USA

In this paper, we use complex analytic functions to achieve independent component analysis (ICA) by maximization of non-Gaussianity and introduce the complex maximization of non-Gaussianity (CMN) algorithm. We derive both a gradient-descent and a quasi-newton algorithm that use the full second-order statistics providing superior performance with circular and noncircular sources as compared to existing methods. We show the connection among ICA methods through maximization of non-Gaussianity, mutual information, and maximum likelihood (NIL) for the complex case, and emphasize the importance of density matching for all three cases. Local stability conditions are derived for the CMN cost function that explicitly show the effects of noncircularity on convergence and demonstrated through simulation examples.

关键词： complex-valued data independent component analysis (ICA) quasi-newton 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：