检索结果-内蒙古大学图书馆

High-Dimensional Volatility Matrix Estimation with Cross-Sectional Dependent and Heavy-Tailed Microstructural Noise

Journal of Systems science & Complexity 2023年第5期36卷 2125-2154页

作者： LIANG Wanwan WU Ben FAN Xinyan JING Bingyi ZHANG Bo Center for Applied Statistics School of StatisticsInstitute of Probability and StatisticsRenmin University of ChinaBeijing 100086China Department of Statistics&Data Science Southern University of Science and TechnologyShenzhen 518055China

The estimates of the high-dimensional volatility matrix based on high-frequency data play a pivotal role in many financial ***,most existing studies have been built on the sub-Gaussian and cross-sectional independence assumptions of microstructure noise,which are typically violated in the financial *** this paper,the authors proposed a new robust volatility matrix estimator,with very mild assumptions on the cross-sectional dependence and tail behaviors of the noises,and demonstrated that it can achieve the optimal convergence rate n-1/***,the proposed model offered better explanatory and predictive powers by decomposing the estimator into low-rank and sparse components,using an appropriate regularization *** studies demonstrated that the proposed estimator outperforms its competitors under various dependence structures of microstructure ***,an extensive analysis of the high-frequency data for stocks in the Shenzhen Stock Exchange of China demonstrated the practical effectiveness of the estimator.

关键词： Cross-sectional dependence high-dimensional data high-frequency data integrated volatility matrix market microstructure noise

来源：评论

学校读者我要写书评

暂无评论

Neural quantum embedding: Pushing the limits of quantum supervised learning

引用

Physical Review A 2024年第2期110卷 022411-022411页

作者： Tak Hur Israel F. Araujo Daniel K. Park Department of Statistics and Data Science Department of Applied Statistics

Quantum embedding is a fundamental prerequisite for applying quantum machine learning techniques to classical data and has substantial impacts on performance outcomes. In this study, we present neural quantum embedding (NQE), a method that efficiently optimizes quantum embedding beyond the limitations of positive and trace-preserving maps by leveraging classical deep-learning techniques. NQE enhances the lower bound of the empirical risk, leading to substantial improvements in classification performance. Moreover, NQE improves robustness against noise. To validate the effectiveness of NQE, we conduct experiments on IBM quantum devices for image data classification, resulting in a remarkable accuracy enhancement from 0.52 to 0.96. In addition, numerical analyses highlight that NQE simultaneously improves the trainability and generalization performance of quantum neural networks, as well as of the quantum kernel method.

关键词： Deep learning Machine learning Quantum algorithms Quantum information theory

来源：评论

学校读者我要写书评

暂无评论

Optimizing ASReview Simulations:A generic Multiprocessing Solution for“Light-data'and“Heavy-data'Users

引用

data Intelligence 2024年第2期6卷 320-343页

作者： Sergei Romanov Abel Soares Siqueira Jonathan de Bruin Jelle Teijema Laura Hofstee Rens van de Schoot Applied Data Science Department of Information and Computing ScienceFaculty of ScienceUtrecht University Netherlands eScienceCenter AmsterdamNL Department of Research and Data Management Services Information Technology ServicesUtrecht UniversityUtrechtthe Netherlands Department of Methodology and Statistics Faculty of Social and Behavioral SciencesUtrecht University

Active learning can be used for optimizing and speeding up the screening phase of systematic *** simulation studies mimicking the screening process can be used to test the performance of different machine-learning models or to study the impact of different training *** paper presents an architecture design withamultiprocessing computational strategyforrunningmanysuch simulation studiesinparallel,using the ASReview Makita workflow generator and Kubernetes software for deployment with cloud *** provide a technical explanation of the proposed cloud architecture and its *** addition to that,we conducted 1140 simulations investigating the computational time using various numbers of CPUs and RAM *** analysis demonstrates the degree to which simulations can be accelerated with multiprocessing computing *** parallel computation strategy and the architecture design that was developed in the present paper can contribute to future research with more optimal simulation time and,at the same time,ensure the safe completion of the needed processes.

关键词： Active learning Systematic review Simulation study Multiprocessing Cloud architecture

来源：评论

学校读者我要写书评

暂无评论

Causally Disentangled Generative Variational AutoEncoder 26

Causally Disentangled Generative Variational AutoEncoder

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： An, SeungHwan Song, Kyungwoo Jeon, Jong-June Department of Statistics University of Seoul Korea Republic of Department of Applied Statistics Department of Statistics and Data Science Yonsei University Korea Republic of

ISBN: (纸本)9781643684369

We present a new supervised learning technique for the Variational AutoEncoder (VAE) that allows it to learn a causally disentangled representation and generate causally disentangled outcomes simultaneously. We call this approach Causally Disentangled Generation (CDG). CDG is a generative model that accurately decodes an output based on a causally disentangled representation. Our research demonstrates that adding supervised regularization to the encoder alone is insufficient for achieving a generative model with CDG, even for a simple task. Therefore, we explore the necessary and sufficient conditions for achieving CDG within a specific model. Additionally, we introduce a universal metric for evaluating the causal disentanglement of a generative model. Empirical results from both image and tabular datasets support our findings. © 2023 The Authors.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Stretched non-negative matrix factorization

引用

npj Computational Materials 2024年第1期10卷 1248-1262页

作者： Ran Gu Yevgeny Rakita Ling Lan Zach Thatcher Gabrielle E.Kamm Daniel O’Nolan Brennan Mcbride Allison Wustrow James R.Neilson Karena W.Chapman Qiang Du Simon J.L.Billinge NITFID School of Statistics and Data ScienceNankai UniversityTianjinChina Department of Applied Physics and Applied Mathematics Fu Foundation School of Engineering&Applied SciencesColumbia UniversityNew YorkNYUSA Department of Chemistry Stony Brook UniversityStony BrookNYUSA Department of Chemistry Colorado State UniversityFort CollinsCOUSA

A novel algorithm,STRETCHEDNMF,is introduced for non-negative matrix factorization(NMF),accounting for signal stretching along the independent variable’s *** addresses signal variability caused by stretching,proving beneficial for analyzing data such as powder diffraction at varying *** approach provides a more meaningful decomposition,particularly when the component signals resemble those from chemical components in the *** STRETCHEDNMF model introduces a stretching factor to accommodate signal expansion,solved using discretization and Block Coordinate Descent *** experimental results indicate that the STRETCHEDNMF model outperforms conventional NMF for datasets exhibiting such *** enhanced version,SPARSE-STRETCHEDNMF,optimized for powder diffraction data from crystalline materials,leverages signal sparsity for accurate extraction,especially with small *** results showcase its effectiveness in analyzing diffraction data,including success in real-time chemical reaction experiments.

关键词： signal stretching matrix

来源：评论

学校读者我要写书评

暂无评论

Developing a Customer Churn Prediction Framework Using LFMCP Value Segmentation: Insights from the Thai Insurance Sector 11th

Developing a Customer Churn Prediction Framework Using LFMCP...

引用

11th International Symposium on Integrated Uncertainty in Knowledge Modelling and Decision Making, IUKM 2025

作者： Pongsathornwiwat, Akkaranan Kulmanochwong, Pattaraporn Department of Logistics Management Graduate School of Applied Statistics National Institute of Development Administration Bangkok Thailand Department of Business Analytics and Data Science Graduate School of Applied Statistics National Institute of Development Administration Bangkok Thailand

ISBN: (纸本)9789819646029

This study explores the application of the Length, Frequency, Monetary, Claim, and Profit (LFMCP) customer value model to predict customer churn in a Thai general insurance company with a primary focus on B2B clients. The research provides valuable insights into the insurance industry, particularly for organizations aiming to enhance customer retention strategies. The churn prediction model is developed in two phases. In the first phase, LFMCP variables are used to distinguish between valued and non-valued customers. In the second phase, the classification performance of five predictive techniques—k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Decision Tree, Random Forest (RF), and XGBoost (XGB)—is compared. Results show that LFMCP significantly improves churn classification, with XGBoost emerging as the best-performing method. The study also investigates the importance of LFMCP variables using the Analytical Hierarchy Process (AHP). While the analysis explores varying weight configurations, findings suggest that equal weighting of the LFMCP variables results in superior predictive performance for churn classification in the insurance context. By incorporating additional predictors beyond the traditional RFM (Recency-Frequency-Monetary) model, the study introduces a novel and effective framework for churn prediction in the insurance industry. This expanded model, combined with insights from the AHP evaluation, forms the key contribution of the research, offering practical value for enhancing decision-making and customer retention strategies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Monitoring photochemical pollutants based on symbolic interval-valued data analysis

引用

Advances in data Analysis and Classification 2023年第4期17卷 897-926页

作者： Lin, Liang-Ching Guo, Meihui Lee, Sangyeol Department of Statistics and Institute of Data Science National Cheng Kung University Tainan Taiwan Department of Applied Mathematics National Sun Yat-sen University Kaohsiung Taiwan Department of Statistics Seoul National University Seoul08826 Korea Republic of

This study considers monitoring photochemical pollutants for anomaly detection based on symbolic interval-valued data analysis. For this task, we construct control charts based on the principal component scores of symbolic interval-valued data. Herein, the symbolic interval-valued data are assumed to follow a normal distribution, and an approximate expectation formula of order statistics from the normal distribution is used in the univariate case to estimate the mean and variance via the method of moments. In addition, we consider the bivariate case wherein we use the maximum likelihood estimator calculated from the likelihood function derived under a bivariate copula. We also establish the procedures for the statistical control chart based on the univariate and bivariate interval-valued variables, and the procedures are potentially extendable to higher dimensional cases. Monte Carlo simulations and real data analysis using photochemical pollutants confirm the validity of the proposed method. The results particularly show the superiority over the conventional method that uses the averages to identify the date on which the abnormal maximum occurred. © 2022, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Control charts

来源：评论

学校读者我要写书评

暂无评论

Interval Estimation Methods for the Variance of a Lognormal Model with Zero Inflation and Their Applications 24

Interval Estimation Methods for the Variance of a Lognormal ...

引用

13th International Conference on Informatics, Environment, Energy and Applications, IEEA 2024

作者： Maneerat, Patcharee Nakjai, Pisit Yosboonruang, Noppadon Niwitpong, Sa-Aat Department Of Data Science Uttaradit Rajabhat University Uttaradit Thailand Department Of Statistics School Of Science University Of Phayao Phayao Thailand Department Of Applied Statistics King Mongkut's University Of Technology North Bangkok Bangkok Thailand

ISBN: (纸本)9798400716423

data on natural rainfall and fish density often exhibit positively right-skewed distributions and include zero observations, thus making them fit a lognormal model with zero inflation. Estimation methods for the variance of a lognormal model with zero inflation using the modified Fletcher (MFL) interval, the generalized confidence interval, and the method of variance estimate recovery are derived herein. The coverage rates and average widths of the proposed methods were assessed via Monte Carlo simulation. Numerical results reveal that the MFL satisfied the requirements for handling large variances, even in situations where the proportion of zero data items was high. Natural rainfall and fish density and data are used to illustrate the efficacies of the proposed methods for estimating rainfall and fish dispersion, respectively. © 2024 Owner/Author.

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

The Star Geometry of Critic-Based Regularizer Learning 38

The Star Geometry of Critic-Based Regularizer Learning

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Leong, Oscar O'Reilly, Eliza Soh, Yong Sheng Department of Statistics and Data Science University of California Los Angeles United States Department of Applied Mathematics and Statistics Johns Hopkins University United States Department of Mathematics National University of Singapore Singapore

Variational regularization is a classical technique to solve statistical inference tasks and inverse problems, with modern data-driven approaches parameterizing regularizers via deep neural networks showcasing impressive empirical performance. Recent works along these lines learn task-dependent regularizers. This is done by integrating information about the measurements and ground-truth data in an unsupervised, critic-based loss function, where the regularizer attributes low values to likely data and high values to unlikely data. However, there is little theory about the structure of regularizers learned via this process and how it relates to the two data distributions. To make progress on this challenge, we initiate a study of optimizing critic-based loss functions to learn regularizers over a particular family of regularizers: gauges (or Minkowski functionals) of star-shaped bodies. This family contains regularizers that are commonly employed in practice and shares properties with regularizers parameterized by deep neural networks. We specifically investigate critic-based losses derived from variational representations of statistical distances between probability measures. By leveraging tools from star geometry and dual Brunn-Minkowski theory, we illustrate how these losses can be interpreted as dual mixed volumes that depend on the data distribution. This allows us to derive exact expressions for the optimal regularizer in certain cases. Finally, we identify which neural network architectures give rise to such star body gauges and when such regularizers have favorable properties for optimization. More broadly, this work highlights how the tools of star geometry can aid in understanding the geometry of unsupervised regularizer learning. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extending finite mixtures of nonlinear mixed-effects models with covariate-dependent mixing weights

引用

Advances in data Analysis and Classification 2024年第2期18卷 271-307页

作者： Wang, Wan-Lun Yang, Yu-Chen Lin, Tsung-I Institute of Statistics National Chung Hsing University Taichung402 Taiwan Department of Public Health China Medical University Taichung404 Taiwan Department of Statistics and Institute of Data Science National Cheng Kung University Tainan701 Taiwan Department of Applied Mathematics National Chung Hsing University Taichung402 Taiwan

Finite mixtures of nonlinear mixed-effects models have emerged as a prominent tool for modeling and clustering longitudinal data following nonlinear growth patterns with heterogeneous behavior. This paper proposes an extended finite mixtures of nonlinear mixed-effects model in which the mixing proportions are related to some explanatory covariates. A logistic function is incorporated to describe the relationship between the prior classification probabilities and the covariates of interest. For parameter estimation, we develop an analytically simple expectation conditional maximization algorithm coupled with the first-order Taylor approximation to linearize the model with pseudo data. The calculation of the standard errors of estimators via a general information-based method and the empirical Bayes estimation of random effects are also discussed. The methodology is illustrated through several simulation experiments and an application to the AIDS Clinical Trials Group Protocol 315 study. © Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Mixtures

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：