检索结果-内蒙古大学图书馆

Heterogeneous tail generalized common factor modeling

Digital Finance 2023年第2期5卷 389-420页

作者： Hediger, Simon Näf, Jeffrey Paolella, Marc S. Polak, Paweł Department of Economics University of Zurich Zurich Switzerland Premedical Project Team INRIA Sophia-Antipolis Montpellier France Department of Banking and Finance University of Zurich Zurich Switzerland Swiss Finance Institute Zurich Switzerland Department of Applied Mathematics and Statistics Stony Brook University Stony Brook NY United States Institute for Advanced Computational Science Stony Brook University Stony Brook NY United States

A multivariate normal mean–variance heterogeneous tails mixture distribution is proposed for the joint distribution of financial factors and asset returns (referred to as Factor-HGH). The proposed latent variable model incorporates a Cholesky decomposition of the dispersion matrix to ensure a rich dependency structure for capturing the stylized facts of the data. It generalizes several existing model structures, with or without financial factors. It is further applicable in large dimensions due to a fast ECME estimation algorithm. The advantages of modelling financial factors and asset returns jointly under non-Gaussian errors are illustrated in an empirical comparison study between the proposed Factor-HGH model and classical financial factor models. While the results for the Fama–French 49 industry portfolios are in line with Gaussian-based models, in the case of highly tail heterogeneous cryptocurrencies, the portfolio based on the Factor-HGH model almost doubles the average return while keeping the volatility, the maximum drawdown, the turnover, and the expected shortfall at a low level. © The Author(s) 2023.

关键词： Asset pricing model C58 Cryptocurrencies expectation maximization algorithm Mixture distribution Portfolio optimization

来源：评论

学校读者我要写书评

暂无评论

GraphHash: Topic-Aware Influence maximization Using Hash

GraphHash: Topic-Aware Influence Maximization Using Hash

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Tang, Qian Guo, Peilin Guo, Jiaqi National University of Defense Technology School of Computer Science Changsha China

ISBN: (纸本)9798350362480

The influence maximization (IM) problem serve as a promising engine for the comprehension of social multimedia. However, current IM solutions often rely on fixed sampling and diffusion probabilities, which are insufficient to cater to the dynamic needs of online advertising, particularly in targeting users with diverse topic preferences. In addition, existing topic-aware IM solutions for online advertising are either time-consuming during the online query phase or burdened with substantial time and space overhead during the offline index construction phase. To solve the above problems, we propose GraphHash, a topic-aware target influence maximization solution that adopts a combination of offline and online phase. GraphHash constructs offline indexes by utilizing hash-based topic probabilities and selects the seed set with the maximal influence through intelligent indexing technique. In addition, we extend GraphHash using bottom-k sketching technology and apply it to different real-world graphs, achieving significant improvements of orders of magnitude over state-of-the-art baselines. © 2024 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

EM-TPACK-SMAR: An Evaluation of Teachers Comprehensive Literacy 2

EM-TPACK-SMAR: An Evaluation of Teachers Comprehensive Liter...

引用

2nd IEEE International Conference on Networks, Multimedia and Information Technology, NMITCON 2024

作者： Shen, Yi Shanghai Communications Polytechnic Shanghai China

ISBN: (纸本)9798350372892

In these days, enrollment of students in education are rapidly increasing so, teaching quality evaluation need to be addressed. Education should have set of quality teaching activities, feedback method is time taking process, cannot assure demands of bright learning environment for evaluating teacher's comprehensive literacy. The expectation-maximization (EM)-Pedagogical Content Knowledge (TPACK)-Substitution Augmentation Modification and Redefinition (SMAR) perspective is proposed which taken input by Personal Knowledge Management (PKM) model where it involves sharing, application, innovation, acquitasation, identification and storage of knowledge. EM algorithm is employed to cluster multi dimensional Gaussian distribution and this used in two different perspectives i.e. TPACK and SMAR include observations of classrooms, lesson plan analysis, videos of classrooms. The proposed EM-TPACK-SMAR perspective model achieved high Precision and recall compared with existing methods i.e. precision 9 4. 3 2 % and recall 9 6. 0 1 %. © 2024 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Poster: Optimizing ABS Deployment via LSTM-based Mobility and Data Traffic Demand Prediction 24

Poster: Optimizing ABS Deployment via LSTM-based Mobility an...

引用

22nd ACM Conference on Embedded Networked Sensor Systems, SenSys 2024

作者： Nam, Jeehee Cho, Anna Park, Jihyun Kim, Chang Kyung Lee, SuKyoung Depart of Computer science Yonsei University Seoul Korea Republic of

ISBN: (纸本)9798400706974

This paper proposes a proactive aerial base station (ABS) deployment framework for hotspots that optimizes the placement of ABSs based on mobility and data traffic demand prediction using a LSTM model. We design a greedy-based ABS deployment algorithm to solve the data rate maximization problem, which is known to be NP-hard. Simulation results demonstrate that the proposed algorithm achieves a higher data rate with fewer ABSs compared to benchmark methods. © 2024 Copyright held by the owner/author(s).

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Risk assessment of water traffic accidents considering coupling effects 12

Risk assessment of water traffic accidents considering coupl...

引用

12th International Conference on Transportation and Traffic Engineering, ICTTE 2023

作者： Kaixuan, Zhang Hanwen, Fan College of Transportation Engineering Dalian Maritime University Dalian China

ISBN: (纸本)9781839539954

To maintain the safety of ship navigation and analyse the relationship between water traffic accidents and their influence factors, this article proposes a two-stage risk assessment model based on correlation analysis method and Bayesian network theory. In the first stage, preselecting the influence factors that affect the severity of water traffic accidents through literature review and expert opinions, considering the correlated characteristics of the influencing factors, Pearson correlation analysis method is used to analyse the relevance between the influencing factors;in the second stage, the Bayesian network theory is used to establish a risk assessment model for water traffic accidents, the parameters of the Bayesian network is trained based on the water traffic accident investigation reports, considering the problem of missing statistical data, the expectation maximization algorithm is used to compensate, then analyse coupling relationship between influencing factors in different scenarios by adjusting the states between different influencing factors. The research results indicate that the two most conflicting factors among single factors are ship factors and personal factors in order;the strongest coupling effect between any two factors is environmental factors and ship factors. The research results can provide theoretical reference for maritime departments to improve ship navigation safety. ©The Institution of Engineering & Technology 2023.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Channel Modeling Using Rayleigh and Rice Sum Approximation 26

Channel Modeling Using Rayleigh and Rice Sum Approximation

引用

2024 IEEE International Conference on Automation/26th Congress of the Chilean Association of Automatic Control, ICA-ACCA 2024

作者： Carvajal, Rodrigo Orellana, Rafael Coronel, Maria Aguero, Juan C. Pontificia Universidad Católica de Valparaíso Escuela de Ingeniería Eléctrica Valparaíso Chile Universidad de Santiago de Chile Departamento de Ingeniería Eléctrica Santiago Chile Universidad Técnológica Metropolitana Departamento de Electricidad Santiago Chile Universidad Técnica Federico Santa María Departamento de Electrónica Valparaíso Chile

ISBN: (纸本)9798350378115

In this paper we develop an identification technique for the multipath wireless channel utilizing a discrete sum distribution approximation. We focus on three of the main distributions for the multi-path channel: Rayleigh, Rice and Nakagami-m. The distributions are approximated using a weighted sum of a Rayleigh and up to three distributions. The estimation procedure is based on the Maximum Likelihood approach and Akaike's Information Criterion. We show via simulations that when the channel is Rayleigh distributed, the estimation yields the correct Rayleigh distribution. When the channel distribution is Rice, the estimation yields one Rician term, whilst when the true channel distribution is Nakagami- m, the estimation yields an adequate approximation with a Rayleigh and Rice terms. © 2024 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Measurement of Utility Harmonic Impedance Based on Gaussian Mixture Model 9

Measurement of Utility Harmonic Impedance Based on Gaussian ...

引用

9th International Conference on Communication, Image and Signal Processing, CCISP 2024

作者： Zhao, Siliang Shu, Qin College of Electrical Engineering Sichuan University Chengdu China

ISBN: (纸本)9798350356656

In the context of accurately measuring harmonic contributions, it is essential to assess both the overall stable harmonic responsibilities and the transient fluctuations to determine if short-term harmonic emissions exceed established standards. Traditional methods often assume that utility-side impedance remains constant in the short term, leading to measurement inaccuracies and inadequate tracking of impedance variations, which are inherently dynamic. This paper introduces a novel approach that models utility impedance using a Gaussian mixture model (GMM). Through this approach, we derive the probability distribution of harmonic voltage at the point of common coupling (PCC). The parameters of this model are estimated using the expectation maximization (EM) algorithm, and utility impedance is subsequently recovered with a least mean squares (LMS) estimator. Our method not only demonstrates superior measurement precision and effective tracking of impedance fluctuations but also surpasses conventional methods by eliminating assumptions such as stable and minimal background harmonics and significantly higher customer-side harmonic impedance compared to the utility-side. Additionally, the proposed GMM method offers a comprehensive measurement scheme capable of accurately calculating average values while dynamically following short-term harmonic impedance fluctuations. © 2024 IEEE.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Cross-validation optimization for large scale hierarchical classification kernel methods 19

引用

20th Annual Conference on Neural Information Processing Systems, NIPS 2006

作者： Seeger, Matthias W. Max Planck Institute for Biological Cybernetics P.O. Box 2169 72012 Tübingen Germany

ISBN: (纸本)9780262195683

We propose a highly efficient framework for kernel multi-class models with a large and structured set of classes. Kernel parameters are learned automatically by maximizing the cross-validation log likelihood, and predictive probabilities are estimated. We demonstrate our approach on large scale text classification tasks with hierarchical class structure, achieving state-of-the-art results in an order of magnitude less time than previous work.

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Stability and Generalization of Stochastic Compositional Gradient Descent algorithms 41

Stability and Generalization of Stochastic Compositional Gra...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Ming Wei, Xiyuan Yang, Tianbao Ying, Yiming Department of Mathematics and Statistics State University of New York at Albany AlbanyNY12222 United States Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States The University of Sydney School of Mathematics and Statistics SydneyNSW2006 Australia

Many machine learning tasks can be formulated as a stochastic compositional optimization (SCO) problem such as reinforcement learning, AUC maximization and meta-learning, where the objective function involves a nested composition associated with an expectation. Although many studies have been devoted to studying the convergence behavior of SCO algorithms, there is little work on understanding their generalization, that is, how these learning algorithms built from training data would behave on future test examples. In this paper, we provide the stability and generalization analysis of stochastic compositional gradient descent algorithms in the framework of statistical learning theory. Firstly, we introduce a stability concept called compositional uniform stability and establish its quantitative relation with generalization for SCO problems. Then, we establish the compositional uniform stability results for two notable stochastic compositional gradient descent algorithms, namely SCGD and SCSC. Finally, we derive dimension-independent excess risk bounds for SCGD and SCSC by balancing stability results and optimization errors. To the best of our knowledge, these are the first-ever known results on stability and generalization analysis of stochastic compositional gradient descent algorithms. Copyright 2024 by the author(s)

关键词： expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

Statistical Model for Battery Recharging Time in RIS-assisted WPT Systems

Statistical Model for Battery Recharging Time in RIS-assiste...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Derbas, Rawan Naser, Shimaa Muhaidat, Sami Khalifa University 6G Research Center Abu Dhabi127788 United Arab Emirates Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

ISBN: (纸本)9798350376715

In this paper, we propose an analytical framework to statistically analyze the battery recharging time (BRT) in reconfigurable intelligent surfaces (RISs)-assisted wireless power transfer (WPT) systems. Specifically, we derive novel expressions for the probability density function (PDF), and cumulative distribution function (CDF) of the BRT of the radio frequency energy harvesting (RFEH) wireless nodes. Considering both the direct link and the links provided by the RIS, the received power at the RFEH nodes is modeled as a gamma mixture model (GMM), where the parameters of GMM are calculated using the expectation-maximization algorithm. Utilizing the derived expressions, we provide a comprehensive analysis for the statistical characterization of the BRT and investigate how the system and battery parameters affect the charging time performance. Finally, simulation results are provided to verify the theoretical results. © 2024 IEEE.

关键词： expectation maximization 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：