检索结果-内蒙古大学图书馆

Distributed pairwise algorithms with gradient descent methods

NEUROCOMPUTING 2019年 333卷 364-373页

作者： Wang, Baobin Hu, Ting South Cent Univ Nationalities Sch Math & Stat Wuhan 430074 Hubei Peoples R China Wuhan Univ Sch Math & Stat Wuhan 430072 Hubei Peoples R China

pairwise algorithms refer to a learning problem with loss functions depending on pairs of examples. There has been remarkable work on analyzing their generalization properties in batch and online settings such as algorithmic stabilities, robustness or regularization. This paper is concerned with distributed pairwise algorithms for dealing with big data, based on a divide-and-conquer strategy. We show that the global estimator of the distributed pairwise algorithm is as good as that of the classical algorithm processing the whole data on a single machine. We present the optimal convergence rate for the distributed pairwise algorithm and provide a theoretical upper bound for the number of local machines under which the optimal rate is retained. Our analysis is achieved by the integral operator decomposition and distributed U-statistics. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Distributed method pairwise algorithms Gradient descent Reproducing kernel Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

Forecasting air transportation demand and its impacts on energy consumption and emission

引用

APPLIED ENERGY 2024年 364卷

作者： Javanmard, Majid Emami Tang, Yili Martinez-Hernandez, J. Adrian Univ Western Ontario Dept Civil & Environm Engn London ON N6A 5B9 Canada Univ Western Ontario Dept Elect & Comp Engn London ON N6A 5B9 Canada

With the increasing demand of passenger and freight air transportation and their key role in energy consumptions, this study developed a hybrid framework integrating machine learning algorithms to predict passenger and freight demand in air transportation and analyzed the impacts of the air transportation demand on energy consumption and CO2 emission. Critical variables are identified through correlation analyses between air transportation characteristics and economic, social, and environmental components, which are further selected to predict the air passenger and freight transportation demand. A hybrid framework is then developed where pairwise machine learning algorithms are developed to enhance prediction accuracy with an optimization model. Furthermore, sensitivity analyses are conducted to assess the effects of passenger and freight demand on energy consumption and CO2 emission. The framework is employed using Canadian air transportation as a case study. The pairwise machine learning algorithms are compared to single algorithm which increases prediction accuracy by 24.5% for passenger demand and by 25.85% for freight demand. It is predicted that the air passenger will increase by 94% to 94.25% and freight transportation demand will increase by 28.12% to 33.97% in 2050 relative to 2019 level. This surge can raise energy consumption and CO2 emission by 8.91% to 9.46% and 11.32% to 12.12% respectively. A 50% decrease in both air passenger and freight transport demand will result in a 5.43% reduction in energy consumption in Canada's transportation sector. Conversely, if demand increases by 50%, CO2 emissions will rise by 3.42% for air passenger transport and 3.67% for air freight transport. The predicted air transportation demand growth and trends can be used for capacity development and emission mitigations for sustainable planning and controls in passenger and freight demand in air transportation.

关键词： Air transportation Demand and energy predictions Machine learning pairwise algorithms Emissions Sensitivity 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：