检索结果-内蒙古大学图书馆

STABILITY IN p-TH MOMENT FOR UNCERTAIN SINGULAR SYSTEMS

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2023年第3期85卷 37-48页

作者： Jia, Zhifu Li, Cunlin School of Sciences and Arts Suqian University Suqian223800 China Ningxia Key Laboratory of intelligent information and Big Data Processing Governance and Social Management Research Center of Northwest Ethnic Regions North Minzu University Yinchuan China

The uncertain singular system is a type of singular system that is disrupted by the canonical Liu process and is described as a multidimensional uncertain differential equation. Although stability in mean, stability in measure, and almost sure stability have been investigated for uncertain singular systems, these three types of stability may not apply in all cases. This paper aims to introduce the concept of stability in p-th moment for uncertain singular systems as a supplementary type of stability. A stability theorem is also presented for uncertain singular systems that are stable in p-th moment. Furthermore, this paper discusses the relationships between stability in measure and stability in p-th moment, between stability in p1-th moment and stability in p2-th moment for uncertain singular systems. An example is provided to demonstrate the effectiveness of our results. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Robust deep auto-encoding network for real-time anomaly detection at nuclear power plants

引用

PROCESS SAFETY AND ENVIRONMENTAL PROTECTION 2022年 163卷 438-452页

作者： Yong, Shi Linzi, Zhang Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China

Detecting anomaly conditions in nuclear reactor is a critical issue in safety management of Nuclear Power Plants (NPPs). Conventionally, the operating status are monitored in transient data with pre-designed labels by human operators or basic diagnosis systems. Nowadays, continuous time series data from multi-sensors are increasingly collected and emerging unlabeled abnormal status are monitored during the operation, making it challenging to capture both spatial and temporal dependency at each time steps without supervised labels. In this paper, a robust unsupervised Multi-Variate Convolutional GRU Encoder-Dncoder (MVCGED) method is proposed to perform anomaly detection and fault diagnosis in multi-sensor operation time series data. Specifically, MVCGED first construct each time steps into signature matrices to maintain both spatial and temporal features via sliding windows with inner-correlation and forget mechanism. Subsequently, A CNN feature extraction network, CNN-based GRU encoding network and CNN decoding network are implemented successively to capture and reconstruct the hidden patterns of the signature matrices. Finally, the reconstruction loss are further utilized to detect anomalies and diagnose faults. Extensive empirical studies based on PCTRAN nuclear power plant operation data demonstrate that MVCGED outperforms commonly-used baseline methods.(c) 2022 Institution of Chemical Engineers. Published by Elsevier Ltd. All rights reserved.

关键词： Nuclear Power Plant Anomaly detection Multi-sensor Time series ConvGRU

来源：评论

学校读者我要写书评

暂无评论

Algorithm-Dependent Generalization of AUPRC Optimization: Theory and Algorithm

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第7期46卷 5062-5079页

作者： Wen, Peisong Xu, Qianqian Yang, Zhiyong He, Yuan Huang, Qingming Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Alibaba Grp Hangzhou Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management BDKM Beijing 101408 Peoples R China

Stochastic optimization of the Area Under the Precision-Recall Curve (AUPRC) is a crucial problem for machine learning. Despite extensive studies on AUPRC optimization, generalization is still an open problem. In this work, we present the first trial in the algorithm-dependent generalization of stochastic AUPRC optimization. The obstacles to our destination are three-fold. First, according to the consistency analysis, the majority of existing stochastic estimators are biased with biased sampling strategies. To address this issue, we propose a stochastic estimator with sampling-rate-invariant consistency and reduce the consistency error by estimating the full-batch scores with score memory. Second, standard techniques for algorithm-dependent generalization analysis cannot be directly applied to listwise losses. To fill this gap, we extend the model stability from instance-wise losses to listwise losses. Third, AUPRC optimization involves a compositional optimization problem, which brings complicated computations. In this work, we propose to reduce the computational complexity by matrix spectral decomposition. Based on these techniques, we derive the first algorithm-dependent generalization bound for AUPRC optimization. Motivated by theoretical results, we propose a generalization-induced learning framework, which improves the AUPRC generalization by equivalently increasing the batch size and the number of valid training examples. Practically, experiments on image retrieval and long-tailed classification speak to the effectiveness and soundness of our framework.

关键词： Optimization Stability analysis Stochastic processes Measurement Standards Approximation algorithms Machine learning algorithms Machine learning AUPRC learning to rank algorithm-dependent generalization stability

来源：评论

学校读者我要写书评

暂无评论

A universal network strategy for lightspeed computation of entropy-regularized optimal transport

引用

NEURAL NETWORKS 2025年 184卷 107038页

作者： Shi, Yong Zheng, Lei Quan, Pei Xiao, Yang Niu, Lingfeng Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Beijing Univ Technol Coll Econ & Management Beijing 100124 Peoples R China Beijing Univ Technol Coll Comp Sci Beijing 100124 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Optimal transport (OT) is an effective tool for measuring discrepancies in probability distributions and histograms of features. To reduce its high computational complexity, entropy-regularized OT is proposed, which is computed through Sinkhorn algorithm and can be readily integrated into neural networks. However, each time the parameters of networks are updated, both the value and derivative of OT need to be calculated. When there is a relatively high demand for solving accuracy, the number of layers in the computation graph for Sinkhorn algorithm is fairly large, requiring plenty of time and memory. To address this problem, we propose a novel network strategy to estimate the transport matrix instead of Sinkhorn algorithm, which significantly reduces the computation graph size. Compared with other neural OT, our method is suitable for arbitrary cost functions and varying marginal distributions. To avoid numerical instability induced by a small regularization coefficient, we devise the new method in log domain with the dual form. We estimate the error bound of the resulting algorithm for approximate inputs in theory, and extend our approach to robust OT and barycenter computation in practice. Extensive experiments show that our method outperforms baselines on both required computation cost and accuracy significantly.

关键词： Optimal transport Entropy regularization Lightspeed computation Neural networks

来源：评论

学校读者我要写书评

暂无评论

A New Augmented Lagrangian Method for MPCCs-Theoretical and Numerical Comparison with Existing Augmented Lagrangian Methods

引用

MATHEMATICS OF OPERATIONS RESEARCH 2022年第2期47卷 1229-1246页

作者： Guo, Lei Deng, Zhibin East China Univ Sci & Technol Sch Business Shanghai 200237 Peoples R China Univ Chinese Acad Sci Chinese Acad Sci Sch Econ & Management Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

We propose a new augmented Lagrangian (AL) method for solving the mathematical program with complementarity constraints (MPCC), where the complementarity constraints are left out of the AL function and treated directly. Two observations motivate us to propose this method: The AL subproblems are closer to the original problem in terms of the constraint structure;and the AL subproblems can be solved efficiently by a nonmonotone projected gradient method, in which we have closed-form solutions at each iteration. The former property helps us show that the proposed method converges globally to an M-stationary (better than C-stationary) point under MPCC relaxed constant positive linear dependence condition. Theoretical comparison with existing AL methods demonstrates that the proposed method is superior in terms of the quality of accumulation points and the strength of assumptions. Numerical comparison, based on problems in MacMPEC, validates the theoretical results.

关键词： mathematical program with complementarity constraints augmented Lagrangian method nonmonotone projected gradient method M-stationarity

来源：评论

学校读者我要写书评

暂无评论

Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning 41

Improving Equivariant Graph Neural Networks on Large Geometr...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yuelin Cen, Jiacheng Han, Jiaqi Zhang, Zhiqiang Zhou, Jun Huang, Wenbing Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Stanford University United States Ant Group China

Equivariant Graph Neural Networks (GNNs) have made remarkable success in a variety of scientific ***, existing equivariant GNNs encounter the efficiency issue for large geometric graphs and perform poorly if the input is reduced to sparse and local graph for speed *** this paper, we propose FastEGNN, an enhanced model of equivariant GNNs on large geometric *** central idea is leveraging a small ordered set of virtual nodes to approximate the large unordered graph of real *** particular, we distinguish the message passing and aggregation for different virtual nodes to encourage mutual distinctiveness, and minimize the Maximum Mean Discrepancy (MMD) between virtual and real coordinates to realize the global *** meets all necessary E(3) symmetries, with certain universal expressivity assurance as *** experiments on Nbody systems (100 nodes), Proteins (800 nodes) and Water-3D (8000 nodes), demonstrate that FastEGNN achieves a promising balance between accuracy and efficiency, and outperforms EGNN in accuracy even after dropping all edges in real systems like Proteins and *** is available at https://***/dhcpack/FastEGNN. Copyright 2024 by the author(s)

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Value FULCRA: Mapping Large Language Models to the Multidimensional Spectrum of Basic Human Values

Value FULCRA: Mapping Large Language Models to the Multidime...

引用

2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2024

作者： Yao, Jing Yi, Xiaoyuan Gong, Yifan Wang, Xiting Xie, Xing Microsoft Research Asia Beijing China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

ISBN: (纸本)9798891761148

Value alignment is crucial for the responsible development of Large Language Models (LLMs). However, how to define values in this context remains largely unexplored. Existing work mainly specifies values as risk criteria formulated in the AI community, e.g., fairness and privacy protection, suffering from poor clarity, adaptability and transparency. Leveraging basic values established in humanity and social science that are compatible with values across cultures, this paper introduces a novel value space spanned by multiple basic value dimensions and proposes BaseAlign, a corresponding value alignment paradigm. Applying the representative Schwartz’s Theory of Basic Values as an instantiation, we construct FULCRA, a dataset consisting of 20k (LLM output, value vector) pairs. LLMs’ outputs are mapped into the K-dim value space beyond simple binary labels, by identifying their underlying priorities for these value dimensions. Extensive analysis and experiments on FULCRA: (1) reveal the essential relation between basic values and LLMs’ behaviors, (2) demonstrate that our paradigm with basic values not only covers existing risks but also anticipates the unidentified ones, and (3) manifest BaseAlign’s superiority in alignment performance with less data, paving the way for addressing the above three challenges. ©2024 Association for Computational Linguistics.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Partial Multi-View Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 11824-11841页

作者： Zhou, Yuan Guo, Yanrong Hao, Shijie Hong, Richang Luo, Jiebo Ministry of Education Hefei University of Technology The Key Laboratory of Knowledge Engineering with Big Data Hefei230009 China Hefei University of Technology The School of Computer Science and Information Engineering Hefei230009 China University of Rochester The Department of Computer Science RochesterNY14627 United States

It is often the case that data are with multiple views in real-world applications. Fully exploring the information of each view is significant for making data more representative. However, due to various limitations and failures in data collection and pre-processing, it is inevitable for real data to suffer from view missing and data scarcity. The coexistence of these two issues makes it more challenging to achieve the pattern classification task. Currently, to our best knowledge, few appropriate methods can well-handle these two issues simultaneously. Aiming to draw more attention from the community to this challenge, we propose a new task in this paper, called few-shot partial multi-view learning, which focuses on overcoming the negative impact of the view-missing issue in the low-data regime. The challenges of this task are twofold: (i) it is difficult to overcome the impact of data scarcity under the interference of missing views;(ii) the limited number of data exacerbates information scarcity, thus making it harder to address the view-missing issue in turn. To address these challenges, we propose a new unified Gaussian dense-anchoring method. The unified dense anchors are learned for the limited partial multi-view data, thereby anchoring them into a unified dense representation space where the influence of data scarcity and view missing can be alleviated. We conduct extensive experiments to evaluate our method. The results on Cub-googlenet-doc2vec, Handwritten, Caltech102, Scene15, Animal, ORL, tieredImagenet, and Birds-200-2011 datasets validate its effectiveness. The codes will be released at https://***/zhouyuan888888/UGDA. © 1979-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Graph classification based fault detection in nuclear power plants with graph formulation 10

Graph classification based fault detection in nuclear power ...

引用

10th International Conference on Information Technology and Quantitative management, ITQM 2023

作者： Qu, Yi Xue, Xiaodong Shi, Yong Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China College of Information Science and Technology University of Nebraska OmahaNE68182 United States

In the routine production and operation of nuclear power plants (NPPs), safety management is extremely important, and consequently, a fault detection system yielding high accuracy could provide effective decision support and prevent the accidents to the maximum extent. Most of existing studies are based on the analysis of time-series data, while researches oriented to the implementation of graph data mining are barely seen. In this paper, we propose an improved fault detection method to address this task from the perspective of graph representation learning. By calculating the similarity between indicators, the multivariate temporal sequences of the running characteristics of NPPs have been formulated as a group of graphs with corresponding labels, on which the graph convolutional network (GCN) has been introduced to detect fault samples in the way of graph classification. Compared to conventional supervised learning classifiers, our proposed methodology performs more superior identification of major faults, and the sensitivity regarding significant parameter or settings in the model design has been analyzed to investigate their optimal arrangements. The findings in this article not only present the promising prospects of introducing graph learning techniques into safety management, also indicate that various kinds of digital signals could be reformulated into graph dataset based on which the original task could be executed more effectively in the way of graph representation learning. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Tenth International Conference on Information Technology and Quantitative management.

关键词： Nuclear power plants

来源：评论

学校读者我要写书评

暂无评论

A hybrid model for stock price prediction based on multi-view heterogeneous data

引用

Financial Innovation 2024年第1期10卷 2411-2460页

作者： Wen Long Jing Gao Kehan Bai Zhichen Lu School of Economics and Management University of Chinese Academy of SciencesBeijing100190People’s Republic of China Research Center on Fictitious Economy and Data Science Chinese Academy of SciencesBeijing100190People’s Republic of China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing100190People’s Republic of China Department of Mathematics Beijing Jiaotong UniversityBeijing100044People’s Republic of China

Literature shows that both market data and financial media impact stock prices;however,using only one kind of data may lead to information ***,this study uses market data and news to investigate their joint impact on stock price ***,combining these two types of information is difficult because of their completely different *** study develops a hybrid model called MVL-SVM for stock price trend prediction by integrating multi-view learning with a support vector machine(SVM).It works by simply inputting heterogeneous multi-view data simultaneously,which may reduce information *** with the ARIMA and classic SVM models based on single-and multi-view data,our hybrid model shows statistically significant *** the robustness test,our model outperforms the others by at least 10%accuracy when the sliding windows of news and market data are set to 1–5 days,which confirms our model’s ***,trading strategies based on single stock and investment portfolios are constructed separately,and the simulations show that MVL-SVM has better profitability and risk control performance than the benchmarks.

关键词： Market data Financial news Support vector machine Multi-view learning Heterogeneous data

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：