检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Wang, Yilong Ye, Haishan Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China Singapore College of Computing and Data Science NTU Singapore

This paper focuses on the large-scale optimization which is very popular in the big data era. The gradient sketching is an important technique in the large-scale optimization. Specifically, the random coordinate descent algorithm is a kind of gradient sketching method with the random sampling matrix as the sketching matrix. In this paper, we propose a novel gradient sketching called GSGD (Gaussian Sketched Gradient Descent). Compared with the classical gradient sketching methods such as the random coordinate descent and SEGA (Hanzely et al., 2018), our GSGD does not require the importance sampling but can achieve a fast convergence rate matching the ones of these methods with importance sampling. Furthermore, if the objective function has a non-smooth regularization term, our GSGD can also exploit the implicit structure information of the regularization term to achieve a fast convergence rate. Finally, our experimental results substantiate the effectiveness and efficiency of our algorithm. Copyright 2024 by the author(s)

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Double Stochasticity Gazes Faster: Snap-Shot Decentralized Stochastic Gradient Tracking Methods 41

Double Stochasticity Gazes Faster: Snap-Shot Decentralized S...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Di, Hao Ye, Haishan Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China College of Computing and Data Science NTU Singapore Singapore

In decentralized optimization, m agents form a network and only communicate with their neighbors, which gives advantages in data ownership, privacy, and scalability. At the same time, decentralized stochastic gradient descent (SGD) methods, as popular decentralized algorithms for training large-scale machine learning models, have shown their superiority over centralized counterparts. Distributed stochastic gradient tracking (DSGT) (Pu & Nedić, 2021) has been recognized as the popular and state-of-the-art decentralized SGD method due to its proper theoretical guarantees. However, the theoretical analysis of DSGT (Koloskova et al., 2021) shows that its iteration complexity is (equation presented) where the doubly stochastic matrix W represents the network topology and CW is a parameter that depends on W. Thus, it indicates that the convergence property of DSGT is heavily affected by the topology of the communication network. To overcome the weakness of DSGT, we resort to the snapshot gradient tracking skill and propose two novel algorithms, snap-shot DSGT (SS DSGT) and accelerated snap-shot DSGT (ASS DSGT). We further justify that SS DSGT exhibits a lower iteration complexity compared to DSGT in the general communication network topology. Additionally, ASS DSGT matches DSGT's iteration complexity (equation presented) under the same conditions as DSGT. Numerical experiments validate SS DSGT's superior performance in the general communication network topology and exhibit better practical performance of ASS DSGT on the specified W compared to DSGT. Copyright 2024 by the author(s)

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Time series prediction and application based on multi-kernel support vector regression 2

Time series prediction and application based on multi-kernel...

引用

2nd International Symposium on Computer Applications and Information Systems, ISCAIS 2023

作者： Yi, Xiaoxing Wen, Xueting Yin, Xiangfeng School of Mathematics and Computational Science Hunan University of Science and Technology Hunan province Xiangtan China School of Mathematics and Computational Science Hunan University of Science and Technology Hunan Engineering Research Center for Big Data and Intelligent Decision-making of Industrial Development Hunan province Xiangtan China

ISBN: (纸本)9781510666665

In this paper, we propose a new MRMRKA-SVR-GARCH model to predict the volatility of time series. This model is a combination of the MRMRKA-SVR model and the GARCH model. Since SVR-GARCH model has been successfully employed to forecast volatility. Empirical results show that the multi-kernel support vector regression based on minimal redundancy maximal correlation criteria and kernel target alignment (MRMRKA-SVR) tend to beat single-kernel SVR models in terms of forecasting accuracy. First,we use the MRMRKA algorithm to select a set of kernels to establish a multi-kernel, and establish the MRMRKA-SVR model. Then we use MRMRKA-SVR to estimate the volatility equation of GARCH model, and establish MRMRKA-SVR-GARCH model. Furthermore, the models’ predictive ability was evaluated using three empirical analysises on China Unicom’s stock price data and stock price data of ICBC. Under different basic kermel numbers m, compare the prediction errors between the proposed model and the SVR-GARCH model based on the mixed Gaussian kernels in the two stock data, the results show that the prediction accuracy of the MRMRKA-SVR-GARCH model fluctuates slightly with the change of m, and the MAE and RMSE of the MRMRKASVR- GARCH model are lower than the mixed-Gaussian-kernel SVR-GARCH model . Description MRMRKA-SVRGARCH model managed to outperform the mixed-Gaussian-kernel SVR-GARCH model. Threrfore, the MRMRKASVR- GARCH model can provide a certain degree of reference in analyzing the trend and prediction of volatility, and has high feasibility and effectiveness. © 2023 SPIE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

The impact of high-speed railway construction on regional economic development in Hubei Province

引用

Management System Engineering 2024年第1期3卷 1-21页

作者： Chen, Yajuan Lv, Yuejiao Zhang, Yanjie School of Management Wuhan University of Technology Wuhan China Research Center for Data Science and Intelligent Decision Making Wuhan University of Technology Wuhan China

Based on the panel data of 16 cities in Hubei Province from 2009 to 2019 (excluding the data during Covid-19 pandemic period), we construct multi-temporal difference-in-differences model (DID) and Spatial Durbin model (SDM) to explore the impact of the High-speed Railway (HSR) construction on the regional economic development in terms of direct economic effect, indirect economic effect and spatial spillover effect. The main conclusions of this paper are as follows: firstly, HSR construction promotes the economic development of cities in Hubei Province in a long time and in a large spatial scope. And the impacts on the economic development are significantly heterogeneous among different types of cities. Also, HSR construction has widened the economic development gap among cities to some extent. Secondly, the upgrading of an industrial structure and the improvement of urbanization level both play mediating roles in the economic impact of HSR construction. Thirdly, the HSR construction has significant spatial spillover effect on economic development, but the spillover effect becomes insignificant with the increase of distance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel Group-FlowSort method for sorting large-scale problems with application to market segmentation

引用

Management System Engineering 2022年第1期1卷 1-16页

作者： Qin, Jindong Guo, Qiuwei Qu, Chenhui School of Management Wuhan University of Technology Wuhan China Research Center for Data Science and Intelligent Decision Making Wuhan University of Technology Wuhan China

In the big data era, promising telecom companies need to develop their user strategies when facing large-scale data. For this purpose, we considered a typical strategy decision problem like market segmentation using a novel group sorting method based on FlowSort and applied it to a real case in the telecom market. A novel Group-FlowSort procedure based on stochastic multi-criteria acceptability analysis (SMAA) was developed for sorting large-scale problems. This method could process and integrate multiple expert opinions to reach a consensus by using the Clustering In QUEst (CLIQUE) algorithm and an improved Jaya algorithm. Furthermore, Group-FlowSort based on SMAA-2 is proposed to eliminate the impact of incomplete preference information and several main characteristics and properties are discussed. In addition, a real case study including 8000 customers and 25 experts is used to illustrate the feasibility of the proposed method for telecom market segmentation. Finally, a comparative analysis with FlowSort-GDSS and sensitivity analysis using SMAA-2 are demonstrated to verify the effectiveness and robustness of the method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Urban system equilibrium model in an asymmetric polycentric city and the influence of rail transit investment

引用

Management System Engineering 2024年第1期3卷 1-16页

作者： Chen, Yajuan Tian, Xin Huang, Han School of Management Wuhan University of Technology Wuhan China Research Center for Data Science and Intelligent Decision Making Wuhan University of Technology Wuhan China

Taking bus and subway into account, an asymmetric polycentric urban system equilibrium model is constructed to explore the impacts of rail transit on the distribution of residents and labor force in a linear polycentric urban system. By comparing the urban system equilibria before and after the introduction of rail transit, the influence of rail transit on urban performance is analyzed. The results show that the introduction of rail transit makes the advantaged center more attractive for the labor force, and further widens the economic level gap between the two business centers. Specifically, larger distance between the two commercial centers and the higher subway travel cost would strengthen the polarization effect caused by rail transit investment. Since the improvement of transportation makes it easier for residents to accept long-distance commuting and they are more willing to choose the jobs in the advanced center.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Double Variance Reduction: A Smoothing Trick for Composite Optimization Problems without First-Order Gradient 41

Double Variance Reduction: A Smoothing Trick for Composite O...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Di, Hao Ye, Haishan Zhang, Yueling Chang, Xiangyu Dai, Guang Tsang, Ivor W. Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China China International Business School Beijing Foreign Studies University Beijing China Singapore College of Computing and Data Science NTU Singapore

Variance reduction techniques are designed to decrease the sampling variance, thereby accelerating convergence rates of first-order (FO) and zeroth-order (ZO) optimization methods. However, in composite optimization problems, ZO methods encounter an additional variance called the coordinate-wise variance, which stems from the random gradient estimation. To reduce this variance, prior works require estimating all partial derivatives, essentially approximating FO information. This approach demands O(d) function evaluations (d is the dimension size), which incurs substantial computational costs and is prohibitive in high-dimensional scenarios. This paper proposes the Zeroth-order Proximal Double Variance Reduction (ZPDVR) method, which utilizes the averaging trick to reduce both sampling and coordinate-wise variances. Compared to prior methods, ZPDVR relies solely on random gradient estimates, calls the stochastic zeroth-order oracle (SZO) in expectation O(1) times per iteration, and achieves the optimal O(d(n+κ) log(1/ϵ)) SZO query complexity in the strongly convex and smooth setting, where κ represents the condition number and ϵ is the desired accuracy. Empirical results validate ZPDVR's linear convergence and demonstrate its superior performance over other related methods. Copyright 2024 by the author(s)

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning on Parkinson's Rat behavior Point Sets in Open Field 20

Deep Learning on Parkinson's Rat behavior Point Sets in Open...

引用

2020 International Symposium on Artificial Intelligence in Medical sciences, ISAIMS 2020

作者： Wu, Lei He, Quan Cao, Hezhi Liu, Long Research Center for Big Data and Intelligent Decision Making School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan Hunan province China Department of Biology and Chemistry National University of Defense Technology Changsha Hunan province China College of Electronic Science and Technology National University of Defense Technology Changsha Hunan province China

ISBN: (纸本)9781450388603

Parkinson's disease (PD) is one of the common progressive neurodegenerative disorder with motor deficits. A substantial volume of research has reported various methods to characterize Parkinson's rat model, but the performances are unsatisfactory. Because of the complexity of behavior data, we can hardly recognize the non-trivial behavioral traits and distinguish the difference between ill rat and the healthy. In this paper, we construct a deep learning model to analyze PD rat behavior data, which is obtained from an optical motion capture system. This system is widely used in movement analysis, robotics, making animations, and can provide high resolution of spatiotemporal information. By using the three-dimensional motion capture technology with retro-reflective optical markers placed in locations that represents rat head and body axis, we can get real-time three-dimensional coordinate information of rat's motion in open field. After the preprocessing, we fed the data set to our model to get a global feature via three abstraction layers and then process them by fully connected layers to obtain the final classification result. The results have shown that this method is robust enough to identify biomechanical and kinematic changes in response to Parkinson's rat with unilateral Striatum lesion. © 2020 ACM.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Enterprise digital management: research review, current status and prospects

引用

Management System Engineering 2024年第1期3卷 1-19页

作者： Han, Xiao Hu, Yixuan Wang, Li Zhou, Rui School of Management Wuhan University of Technology Wuhan China Research Center for Data Science and Intelligent Decision Making Wuhan University of Technology Wuhan China School of Business East China University of Science and Technology Shanghai China

With the advent of the digital economy era, digital management has become a hot topic of concern in both the industry and academia. Focusing on digital management in enterprises, this article consists of 750 CSSCI source journals indexed in the CNKI database from 2000 to 2022, 1303 articles in the literature and Web of science core database were used as research objects, using CiteSpace and VOSviewer Perform bibliometric analysis using visual tools. Firstly, conduct data statistics on the overall collection and apply the author literature coupling method. Analyze representative literature. Secondly, by means of thematic temporal evolution and keyword emergence, we will sort out the development of domestic and foreign research. Expand the context. Next, we use keyword clustering method to explore recent hot topics in domestic and international research. Based on citation analysis and word cluster analysis, with the comprehensive results of "basic elements—management process—management effectiveness", a digital management theory for enterprises has been constructed on the IPO Panoramic Research Framework Model. Finally, future research directions are proposed. Firstly, the issue of digital technology abuse must be addressed through standardized management protocols. Secondly, the mechanisms by which digital technology impacts organizational performance warrant thorough investigation. Thirdly, the paradigm of collaboratively applying multiple digital technologies should be explored. Lastly, the design of an innovative digital ecosystem strategy based on a platform approach needs to be developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint advertising and ordering decisions under the pre-sales crowdfunding

引用

Management System Engineering 2023年第1期2卷 1-14页

作者： Zeng, Kuan Shen, Yaohan School of Management Wuhan Textile University Wuhan China Research Center of Enterprise Decision Support Key Research Institute of Humanities and Social Sciences Wuhan China School of Management Wuhan University of Technology Wuhan China Research Center for Data Science and Intelligent Decision Making Wuhan University of Technology Wuhan China

Our study considers a company launching new product on pre-sales crowdfunding platform and explores the joint advertising and ordering decisions in mass market thereafter. Under the “AON” mechanism, we construct profit-maximizing models to examine the impact of pledged amount on the company’s decision on advertising expense, order quantity and funding target. The results show that the optimal order quantity increases with the pledged amount in crowdfunding, and the company won’t promote new product in mass market until the pledged amount reaches a funding threshold, and the advertising expense increases with the pledged amount since then. In addition, we figure out the feasible scope for the funding target and suggest the company set the target within the scope, to ensure the project profitability. Furthermore, we demonstrate that the expected pledged amount won’t increase with the funding target, and the optimal funding target would be the lower bound in its feasible scope, to improve the campaign success. Finally, we conduct numerical analysis to verify our theoretical results.

关键词：

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：