检索结果-内蒙古大学图书馆

arXiv 2020年

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

This paper focuses on generalization performance analysis for distributed algorithms in the framework of learning theory. Taking distributed kernel ridge regression (DKRR) for example, we succeed in deriving its optimal learning rates in expectation and providing theoretically optimal ranges of the number of local processors. Due to the gap between theory and experiments, we also deduce optimal learning rates for DKRR in probability to essentially reflect the generalization performance and limitations of DKRR. Furthermore, we propose a communication strategy to improve the learning performance of DKRR and demonstrate the power of communications in DKRR via both theoretical assessments and numerical experiments. Copyright © 2020, The Authors. All rights reserved.

关键词： Regression analysis

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

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

Carbon futures price forecasting based with ARIMA-CNN-LSTM model

引用

Procedia Computer science 2019年 162卷 33-38页

作者： Lei Ji Yingchao Zou Kaijian He Bangzhu Zhu School of Business Hunan University of Science and Technology Xiangtan411201China Hunan Engineering Research Center for Industrial Big Data and Intelligent Decision Making Hunan University of Science and Technology Xiangtan 411201 China College of Information Science and Technology Beijing University of Chemical Technology Beijing 100029 China Business School Nanjing University of Information Science & Technology Nanjing 210044 China

In this paper, we introduced an ARIMA-CNN-LSTM model to forecast the carbon futures price. The ARIMA-CNN-LSTM model employs the ARIMA model and the deep neural network structure that combines the CNN and LSTM layers to capture linear and nonlinear data features. In ARIMA-CNN-LSTM model structure, the ARIMA is used to capture the linear features. The Convolutional Neural Network (CNN) is used to capture the hierarchical data structure while the Long Short Term Memory network (LSTM) is used to capture the long-term dependencies in the data. Comprehensive performance evaluation has been conducted using weekly carbon futures price. Results have confirmed that ARIMA-CNN-LSTM model can achieve better prediction accuracy than the benchmark models, in terms of Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) performance measures.

关键词： Carbon futures price forecasting deep learning model ARIMA model Convolutional Neural Network (CNN) Long Short-Term Memory Network (LSTM)

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

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

arXiv

引用

arXiv 2020年

作者： Ye, Haishan Luo, Luo Zhou, Ziang Zhang, Tong 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 Computer Science & Mathematics The Hong Kong University of Science and Technology Hong Kong

关键词： Convex optimization

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

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

arXiv

引用

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

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：