检索结果-内蒙古大学图书馆

arXiv 2024年

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∈ )) SZO query complexity in the strongly convex and smooth setting, where κ represents the condition number and ∈ is the desired accuracy. Empirical results validate ZPDVR's linear convergence and demonstrate its superior performance over other related methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Media Attention and ESG Greenwashing: Evidence from Chinese Listed Companies

SSRN

引用

SSRN 2023年

作者： Jiang, Cuixia Li, Xiuxiu Xu, Qifa Liu, Junhang School of Management Hefei University of Technology Anhui Hefei230009 China Philosophy and Social Sciences Laboratory of Data Science and Smart Society Governance Ministry of Education Anhui Hefei230009 China Key Laboratory of Process Optimization and Intelligent Decision-Making Ministry of Education Anhui Hefei230009 China Ministry of Education Engineering Research Center for Intelligent Decision-Making & Information System Technologies Anhui Hefei230009 China

We investigate the relationship between media attention and environmental, social, and governance (ESG) greenwashing using the data of Chinese A-share listed companies from 2011 to 2020. Our results show that media attention can inhibit corporate ESG greenwashing behavior. Moreover, this inhibiting effect is mainly caused by paper media and becomes more prominent in non-state-owned enterprises (non-SOEs). The mediation analysis proves that media attention plays an important role in improving investor attention, thereby inhibiting corporate ESG greenwashing. The moderation analysis indicates that the effect of media attention on inhibiting ESG greenwashing is weakened in companies with more analyst following and higher quality of internal control. Our study provides a new view on the governance of ESG greenwashing in China. © 2023, The Authors. All rights reserved.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Can Gaussian sketching converge faster on a preconditioned landscape? 24

Can Gaussian sketching converge faster on a preconditioned l...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Yilong Wang Haishan Ye 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 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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Stream Concept-cognitive Computing System for Streaming data Learning

TechRxiv

引用

TechRxiv 2023年

作者： Mi, Yunlong Liu, Wenqi Shi, Yong The Big Data and Intelligent Decision Making Research Center Central South University Changsha410083 China The Data Science Research Center Kunming University of Science and Technology Kunming650500 China The Faculty of Science Kunming University of Science and Technology Kunming650500 China The School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China The Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

People can often acquire knowledge dynamically and rapidly from different types of data, yet existing incremental learning algorithms are still computationally time consuming and most of stream learning methods are mainly designed for streaming data while ignoring other types of data. Hence, this paper proposes a novel dynamic concept learning (CL) algorithm by imitating human cognitive learning processes from the perspective of brain logical cognition, which is named stream concept-cognitive computing system (streamC3S). For streamC3S, it mainly consists of three aspects: the concept space, CL process, and model update process. Moreover, considering the concept drift frequently occurs in the streaming data over time, an extended version of streamC3S (namely, streamC3SE) is also proposed in this work. Specifically, we first show the related theories for streamC3S and streamC3SE on the basis of the concept space. Then an overall framework and its corresponding algorithm are shown. Finally, experimental results on various types of datasets, including the standard machine learning datasets, streaming datasets, image datasets, and two traffic data streams, validate the effectiveness of our streamC3S and streamC3SE compared to the state-of-the-art incremental learning and stream learning algorithms. © 2023, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

ISMI-VAE: A deep learning model for classifying disease cells using gene expression and SNV data

引用

Computers in Biology and Medicine 2024年 175卷 108485-108485页

作者： Li, Han Zhou, Yitao Zhao, Ningyuan Wang, Ying Lai, Yongxuan Zeng, Feng Yang, Fan Department of Automation Xiamen University Xiamen China National Institute for Data Science in Health and Medicine Xiamen University Xiamen361005 China Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision Making Xiamen university Xiamen361000 China School of Informatics Xiamen University Xiamen China State Key Laboratory of Cellular Stress Biology School of Life Sciences Xiamen University China Research Unit of Cellular Stress of CAMS Cancer Research Center School of Medicine Xiamen University China

Various studies have linked several diseases, including cancer and COVID-19, to single nucleotide variations (SNV). Although single-cell RNA sequencing (scRNA-seq) technology can provide SNV and gene expression data, few studies have integrated and analyzed these multimodal data. To address this issue, we introduce Interpretable Single-cell Multimodal data Integration Based on Variational Autoencoder (ISMI-VAE). ISMI-VAE leverages latent variable models that utilize the characteristics of SNV and gene expression data to overcome high noise levels and uses deep learning techniques to integrate multimodal information, map them to a low-dimensional space, and classify disease cells. Moreover, ISMI-VAE introduces an attention mechanism to reflect feature importance and analyze genetic features that could potentially cause disease. experimental results on three cancer data sets and one COVID-19 data set demonstrate that ISMI-VAE surpasses the baseline method in terms of both effectiveness and interpretability and can effectively identify disease-causing gene features. © 2024 Elsevier Ltd

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Universal data-Driven Spatial Interpolation Framework for the Measurements of Environmental Sites

SSRN

引用

SSRN 2023年

作者： Cheng, Zhen Guo, Yuzhe Xue, Wenbo Du, Qinyi Shanghai Environmental Protection Key Lab of Environmental Big Data and Intelligent Decision-making School of Environmental Science and Engineering Shanghai Jiao Tong University Shanghai China Center of Air Quality Simulation and System Analysis Chinese Academy of Environmental Planning Beijing100043 China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

The accurate spatial distribution of environmental pollutant metrics is crucial for evaluating human exposure and managing the environment. Spatial interpolation, which relies on the measurements of limited environmental sites, is often necessary. However, commonly used geostatistical methods often introduce significant prediction biases, leading to misleading assessments and decision-making processes. Reported machine learning studies usually required intensive spatial datasets and sites’ measurements, as well as special complex algorithm for target pollutant. In this study, we propose and validate a simple and universal data-driven spatial interpolation framework for environmental sites’ measurements. We employ a conditional generative adversarial network (cGAN) as the data-driven algorithm to leverage spatial dataset. We demonstrate the implementation and validation of the framework using two representative ambient pollutants, namely ozone and PM2.5. The results reveal a relative mean absolute error of only 9% for ozone and 13% for PM2.5. Compared to the traditional inverse distance weight method and ordinary kriging method, the proposed framework reduces errors by 70% and 79% respectively. Furthermore, the R-squared values between independent measurements from additional geographic locations and the corresponding predicted results using the proposed method reach 0.96 for ozone and 0.97 for PM2.5, showcasing its excellent and consistent performance. The unique input dataset and universal algorithm architecture illustrate the distinct advantages compared to previous machine learning studies. With the rapid increase of remote sensing and numerical modeling datasets in the environmental field, we anticipate that data-driven methods will replace traditional mathematical approaches. This study provides a simple yet universal interpolation framework and is expected to accelerate the adoption of these advancements. © 2023, The Authors. All rights reserved.

关键词： Spatial distribution

来源：评论

学校读者我要写书评

暂无评论

Universal consistency of deep convolutional neural networks

arXiv

引用

arXiv 2021年

作者： Lin, Shao-Bo Wang, Kaidong Wang, Yao Zhou, Ding-Xuan Center for Intelligent Decision-Making and Machine Learning School of Management Xi'an Jiaotong University Xi'an710049 China School of Data Science Department of Mathematics City University of Hong Kong Hong Kong Hong Kong

Compared with avid research activities of deep convolutional neural networks (DCNNs) in practice, the study of theoretical behaviors of DCNNs lags heavily behind. In particular, the universal consistency of DCNNs remains open. In this paper, we prove that implementing empirical risk minimization on DCNNs with expansive convolution (with zero-padding) is strongly universally consistent. Motivated by the universal consistency, we conduct a series of experiments to show that without any fully connected layers, DCNNs with expansive convolution perform not worse than the widely used deep neural networks with hybrid structure containing contracting (without zero-padding) convolution layers and several fully connected layers. © 2021, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

The Temporal Structural Pattern in Scientific Collaborative Behavior from the Perspective of Complex Network 23rd

The Temporal Structural Pattern in Scientific Collaborative...

引用

23rd International Symposium on Knowledge and Systems sciences, KSS 2024

作者： Zholdoshbaeva, Elina Zhang, Shuang Liu, Feifan Xia, Haoxiang Institute of Systems Engineering Dalian University of Technology No. 2 Linggong Road Liaoning Dalian116024 China Center for Big Data and Intelligent Decision-Making Dalian University of Technology Linggong Road Liaoning Dalian116024 China School of Business East China University of Science and Technology 130 Meilong Road Xuhui District Shanghai200237 China Institute for Advanced Intelligence Dalian University of Technology Linggong Road Liaoning Dalian116024 China Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education of China Linggong Road Liaoning Dalian116024 China

ISBN: (纸本)9789819601776

The rapid advancement of science has underscored the importance of collaboration among scientists. While many studies have explored the structure of collaboration networks, there is a lack of comprehensive quantitative research on the temporal patterns of these collaborations. This study addresses this gap by analyzing temporal scientific collaboration networks in physics, spanning from 1960 to 2021, using complex network theories and methods. By constructing five-year temporal collaborative networks and employing metrics such as network diameter, shortest path, and clustering coefficient, this research reveals an increase in connectivity and small-world characteristics over time. Additionally, community detection highlights a shift towards specialized collaboration patterns and increased cross-community interactions. The study also uncovers growing centrality and social stratification within the research system, with the "rich club" phenomenon indicating strong and dynamic collaborations among highly connected scientists. Temporal analysis shows that while ultra-high connectivity scientists engage in fluctuating relationships, medium-high connectivity scientists maintain more stable collaborations. These findings provide insights into the evolution of collaborative behaviors and inform science policy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Collaborative learning

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

Smart surgical telementoring system with patch-to-pixel point tracking method

EngMedicine

引用

EngMedicine 2025年第1期2卷

作者： Yanwei Qu Ling Li Tongtong Li Jieyu Zheng Wentao Tang Xiaojian Li School of Management Hefei University of Technology Hefei 230009 Anhui China Philosophy and Social Sciences Laboratory of Data Science and Smart Society Governance Ministry of Education Hefei 230009 Anhui China Key Laboratory of Process Optimization and Intelligent Decision-making Ministry of Education Hefei 230009 Anhui China Hefei Haochuan Information Technology Co. Ltd Hefei 230088 Anhui China Ministry of Education Engineering Research Center for Intelligent Decision-Making Information System Technologies Hefei 230009 Anhui China

The utilization of surgical telementoring has become increasingly prevalent in enhancing the surgical standards of grassroots hospitals in contemporary times. In the traditional framework of surgical telementoring, remote doctors guide grassroots doctors via video and audio communication, which may encounter obstacles such as inadequate information transfer and challenges in accurately pinpointing the surgical site and path. To mitigate these issues, this study introduces an intelligent surgical telementoring system based on edge computing. This system enables the transmission of points marked by remote doctors to grassroots doctors, updating these points’ coordinates in real-time on the local endoscopic video. In this system, a novel method named P2PTracking (Patch-to-Pixel Point Tracking) is implemented. This process begins with the tracking of a square patch surrounding the point marked by the remote doctor using SiameseFC. Following this, feature matching is performed on the tracked patch in the current frame and the square patch in the labelled frame or template frame. The affine transformation is then calculated based on the feature matching results. Lastly, the point tracking result is derived using the computed affine transformation. experimental results indicate that the proposed system has a transmission speed of 1.99M/s and a transmission latency of 171 ms when transmitting video at a resolution of 1920 × 1080px, while the proposed method can achieve an accuracy of 96.6 % when the pixel error is 4. The code and data are available at https://***/hfut66/*** .

关键词： Surgical telementoring Patch tracking Point tracking Feature matching Template update mechanism

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：