检索结果-内蒙古大学图书馆

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

Environmental information perception enhances cooperation in stochastic public goods games via Q-learning

引用

Applied Mathematics and Computation 2025年 504卷

作者： Li, Yipeng Hu, Xiangyue Jin, Xing Zhang, Huizhen Yang, Jiajia Wang, Zhen School of Cyberspace Hangzhou Dianzi University Zhejiang Hangzhou310018 China Zhuoyue Honors College Hangzhou Dianzi University Zhejiang Hangzhou310018 China Experimental Center of Data Science and Intelligent Decision-Making Hangzhou Dianzi University Zhejiang Hangzhou310018 China

Cooperation is the foundation of social progress, but due to rational individuals often prioritize personal interests, reciprocal cooperation is undermined. The Public Goods Game (PGG) is a classic model for studying group interactions. Traditional PGG assumes a static environment, but in reality, the environment is dynamically changing, and there is an interaction between individual behavior and the environment. Therefore, the stochastic game framework is proposed and applied to study the feedback mechanisms between behavior and the environment. This paper takes the two-state environmental transition mechanism as an example to explore the impact of environmental information perception ability on individual decision-making in the stochastic PGG. Specifically, we use the Q-learning algorithm to depict individual decision-making behavior and consider two types of individuals with different perception abilities: individuals with environmental perception ability select the best action based on the current environmental state, while individuals without environmental perception ability make decisions based solely on historical experience. The experimental results show that environmental information perception significantly lowers the cooperation threshold in the stochastic PGG. By analyzing the microscopic interaction modes of individuals, we find that there is an isolation zone effect between different strategy populations, which effectively prevents the erosion of defection behaviors and ensures the internal stability of cooperation. The extended experiments further validate the robustness of the results. This study shows that environmental information is beneficial for promoting the evolution of cooperation. These findings provide new insights into the cooperation mechanisms in stochastic PGG and offer valuable guidance for promoting cooperation in real-world societies. © 2025 Elsevier Inc.

关键词： decision making

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

Volunteer rescue dispatch during the Coronavirus Disease 2019 epidemic:Using the recruitment of volunteers for pneumonia epidemic prevention and control in Chun’an County as an example

引用

Journal of Safety science and Resilience 2022年第4期3卷 330-339页

作者： Liting Chen Shengqun Chen Jing Zheng Jianqing Gao College of Electronics and Information Science Fujian Jiangxia UniversityFuzhou 350108China Research Institute for Data Analysis and Intelligent Decision-Making Fujian Jiangxia UniversityFuzhou 350108China School of Information Engineering Fujian Business UniversityFuzhou 350012China Fujian Provincial Universities Engineering Research Center of Big Data Analytics for Business Intelligence Fujian Business UniversityFuzhou 350012China

To solve the problem of volunteer dispatch during the Coronavirus Disease 2019(COVID-19)epidemic,a many-to-many two-sided matching volunteer dispatch method based on an improved predator-search algorithm is ***,different evaluation index sets for volunteers and rescue tasks were developed,and weightings were determined using the analytic hierarchy ***,the actual and expected values of the different indicators of the two parties were determined,and the triangular fuzzy number was used to calculate the satis-faction of the two *** on this number,we used a linear weighting method to calculate the combined satisfaction and build a many-to-many two-sided matching model according to the demands of both ***-sequently,an improved predator-search algorithm was used to solve the ***,taking the recruitment of volunteers for pneumonia epidemic prevention and control in Chun’an County as an example,the method proposed in our study was verified.A comparison and analysis of the results further demonstrated the feasibility and advantages of this method.

关键词： Volunteer Many-to-many Two-sided matching Predator-search algorithm

来源：评论

学校读者我要写书评

暂无评论

SETAR Model Research Based on Support Vector Regression Parameter Estimation Method and Empirical Analysis 3

SETAR Model Research Based on Support Vector Regression Para...

引用

2021 3rd International Conference on Robotics, intelligent Control and Artificial Intelligence, ICRICA 2021

作者： Li, Yun Yin, Xiangfeng Wen, Xueting School of Mathematics and Computational Science Hunan University of Science and Technology Xiangtan China Sch. 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 Xiangtan China

In this paper, we use support vector regression (SVR) to estimate the parameters of the SETAR model for predicting the log-return of stock price data. SETAR model is usually estimated using maximum likelihood (ML) and minimize conditional sum-of-squares (CSS), assuming that the data are normal distribution. SVR is a powerful tool for regression estimation. Therefore, this paper proposes to use SVR instead of maximum likelihood and conditional least squares to estimate the parameters of the SETAR model. Empirical analysis on the two stock price data of China Unicom and ICBC, the results show that on the data of China Unicom, the prediction error of the Gaussian kernel SVR-SETAR model is 8% lower than that of the ML-SETAR model and the CSS-SETAR model. And on ICBC data, the prediction error of the Gaussian kernel SVR-SETAR model is 26.32% and 20% lower than that of the ML-SETAR model and CSS-SETAR model, respectively. This suggests that SVR can be used to estimate the parameters of the SESAT model and the SVR-SETAR model has higher predictive power. © Published under licence by IOP Publishing Ltd.

关键词： Normal distribution

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

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

Probabilistic Electricity Price Forecasting and Uncertainty Estimation Using Deep Bayesian Model with Multi-Distribution Fusion

SSRN

引用

SSRN 2024年

作者： Shao, Zhen Han, Yating Fu, Chao Zha, Jianrui Yang, Shanlin School of Management Hefei University of Technology Hefei230009 China Key Laboratory of Process Optimization and Intelligent Decision-making Ministry of Education Anhui Hefei230009 China Philosophy and Social Sciences Laboratory of Data Science and Smart Society Governance Hefei University of Technology Ministry of Education Hefei230009 China Ministry of Education Engineering Research Center for Intelligent Decision-Making & Information System Technologies Hefei230009 China

Probabilistic electricity price forecasting (EPF) is paramount for stakeholder scheduling and trading in deregulated energy markets. However, during the process of establishing a probability prediction model, the consequential aleatoric and epistemic uncertainties are indistinguishable. Moreover, identifying epistemic uncertainty rather than aleatoric uncertainty is significant for conducting credible probabilistic EPF in cases with expected and unexpected fluctuations. This article proposes a hybrid approach under a Bayesian probability framework for performing reliable and accurate probabilistic forecasting. Specifically, it applies Bayesian deep learning model to convey the latent probability distribution of electricity prices, which represents the desirable epistemic uncertainty and inevitable aleatoric uncertainty. The embedded architecture employs a multi-head attention mechanism (MHAM) to allocate previous hidden states of long short-term memory (LSTM) cells, detecting both the local and global price patterns simultaneously. Considering the forecasting bias arising from aleatoric uncertainty in the process of establishing Bayesian networks, a new Wasserstein distance-based multi-distribution fusion mechanism driven by evidence theory is proposed and employed to identify and mitigate the aleatoric uncertainty of credible probabilistic EPF problems. The effectiveness of the proposed approach is evaluated on two real-world electricity price datasets and compared with twelve state-of-the-art models. © 2024, The Authors. All rights reserved.

关键词： Bayesian networks

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 24

Double variance reduction: a smoothing trick for composite o...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Hao Di Haishan Ye Yueling Zhang Xiangyu Chang Guang Dai Ivor W. Tsang Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China and SGIT AI Lab State Grid Corporation of China International Business School Beijing Foreign Studies University Beijing China Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University China SGIT AI Lab State Grid Corporation of China CFAR and IHPC Agency for Science Technology and Research (A*STAR) Singapore and 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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-consensus decentralized accelerated gradient descent

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 14474-14523页

作者： Haishan Ye Luo Luo Ziang Zhou Tong Zhang Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University Xi'an China School of Data Science Fudan University Shanghai China Department of Computing The Hong Kong Polytechnic University Hong Kong China Computer Science & Mathematics The Hong Kong University of Science and Technology Hong Kong China

This paper considers the decentralized convex optimization problem, which has a wide range of applications in large-scale machine learning, sensor networks, and control theory. We propose novel algorithms that achieve optimal computation complexity and near optimal communication complexity. Our theoretical results give affirmative answers to the open problem on whether there exists an algorithm that can achieve a communication complexity (nearly) matching the lower bound depending on the global condition number instead of the local one. Furthermore, the linear convergence of our algorithms only depends on the strong convexity of global objective and it does not require the local functions to be convex. The design of our methods relies on a novel integration of well-known techniques including Nesterov's acceleration, multi-consensus and gradient-tracking. Empirical studies show the outperformance of our methods for machine learning applications.

关键词： consensus optimization decentralized algorithm accelerated gradient descent gradient tracking composite optimization

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：