检索结果-内蒙古大学图书馆

parallel inference for big data with the group Bayesian method

METRIKA 2021年第2期84卷 225-243页

作者： Guo, Guangbao Qian, Guoqi Lin, Lu Shao, Wei Shandong Univ Technol Dept Stat Zibo 255000 Peoples R China Univ Melbourne Sch Math & Stat Parkville Vic 3010 Australia Shandong Univ Sch Math Jinan 250100 Peoples R China Qufu Normal Univ Sch Management Rizhao 276826 Shandong Peoples R China

In recent years, big datasets are often split into several subsets due to the storage requirements. We propose a parallel group Bayesian method for statistical inference in sparse big data. This method improves the existing methods in two aspects: the total datasets are also split into a data subset sequence and the parameter vector is divided into several sub-vectors. Besides, we add a weight sequence to optimize the sub-estimators when each of them has a different covariance matrix. We obtain several theoretical properties of the estimator. The results of numerical simulations show that our method is consistent with the theoretical results and is more effective than classic Markov chain Monte Carlo methods.

关键词： Data subsets Group Gibbs parallel inference

来源：评论

学校读者我要写书评

暂无评论

parallel inference in dynamic decision support systems of a semiotic type

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2004年第4期15卷 505-510页

作者： Vagin, VN Allahverdi, N Tütüncü, K Saraçoglu, R Sulak, SA Moscow Power Res Inst Dept Math Appl Krasnokazarmennaya 14 Moscow 111250 Russia Selcuk Univ Dept Elect & Comp Educ TR-42031 Konya Turkey

The organization of parallel inference in dynamic decision support systems (DDSS) of a semiotic type, oriented towards a solving of ill-formed problems in dynamic applied domains, is considered. As a knowledge representation model, there are used production rules reflecting expert knowledge about a problem domain, an environment and decision making processes. The main concepts and assertions defining possibility and impossibility of parallel executing the production rules are given. Several types of parallelism in an inference process are introduced. The corresponding algorithm of parallel inference is described. Thus, the purpose of this paper is to develop and to research parallel inference methods and procedures that provide efficient processing a large amount of production rules for DDSS of a semiotic type.

关键词： dynamic decision support system sentiotic model parallel execution non-deterministic choice parallel inference

来源：评论

学校读者我要写书评

暂无评论

parallel inference on connection graphs

Parallel inference on connection graphs

引用

Joint Conference on the Science and Technology of Intelligent Systems ISIC/CIRA/ISAS

作者： Vagin, VN Salapina, NO Moscow Power Engn Inst Dept Appl Math Moscow 111250 Russia

ISBN: (纸本)0780344235

The given paper presents a theoretical justification and a description or the practical implementation of the theorem proving problems in the first order predicate logic by using connection graphs. The basic definitions and concepts are given. Two types of parallelism in a process of a deductive inference are introduced. The sequential and parallel inference algorithms are described. The practical implementation of the sequential and parallel inference system is presented and analyzed. The examples of the theorem proving problems are discussed.

关键词： connection graph theorem proving first order predicate logic parallel inference dcdp-parallelism dcdp-parallel resolution parallel resolution

来源：评论

学校读者我要写书评

暂无评论

parallel inference in dynamic decision support systems of a semiotic type

Parallel inference in dynamic decision support systems of a ...

引用

3rd International Symposium on Intelligent Manufacturing Systems

关键词： dynamic decision support system sentiotic model parallel execution non-deterministic choice parallel inference

来源：评论

学校读者我要写书评

暂无评论

Embarrassingly parallel inference for Gaussian Processes

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2019年第1期20卷 1-26页

作者： Zhang, Michael Minyi Williamson, Sinead A. Princeton Univ Dept Comp Sci Princeton NJ 08544 USA Univ Texas Austin Dept Stat & Data Sci Dept Informat Risk & Operat Management Austin TX 78712 USA

Training Gaussian process-based models typically involves an O(N-3) computational bottleneck due to inverting the covariance matrix. Popular methods for overcoming this matrix inversion problem cannot adequately model all types of latent functions, and are often not parallelizable. However, judicious choice of model structure can ameliorate this problem. A mixture-of-experts model that uses a mixture of K Gaussian processes offers modeling flexibility and opportunities for scalable inference. Our embarrassingly parallel algorithm combines low-dimensional matrix inversions with importance sampling to yield a flexible, scalable mixture-of-experts model that offers comparable performance to Gaussian process regression at a much lower computational cost.

关键词： Gaussian process parallel inference machine learning Bayesian non-parametrics

来源：评论

学校读者我要写书评

暂无评论

Automatic Pipeline parallelism: A parallel inference Framework for Deep Learning Applications in 6G Mobile Communication Systems

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年第7期41卷 2041-2056页

作者： Shi, Hongjian Zheng, Weichu Liu, Zifei Ma, Ruhui Guan, Haibing Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn Shanghai 200240 Peoples R China

With the rapid development of wireless communication, achieving the neXt generation Ultra-Reliable and Low-Latency Communications (xURLLC) in 6G mobile communication systems has become a critical problem. Among many applications in xURLLC, deep learning model inference requires improvement over its efficiency. Due to the heterogeneous hardware environment in 6G, parallel schedules from distributed machine learning and edge computing has been borrowed to tackle the efficiency problem. However, traditional parallel schedules suffer from high latency, low throughput, and low device utility. In this paper, we propose Automatic Pipeline parallelism (AP(2)), a parallel inference framework for deep learning applications in 6G mobile communication systems, to improve the model inference efficiency while maintaining reliability. (AP(2)) contains three sub-modules. A task-device affinity predictor predicts a task's expected execution time on a given device. The parallel inference arrangement optimizer finds the most suitable device for each task. The parallel inference scheduler converts the arrangement to a schedule that can be directly executed in the system. The experimental results show that (AP(2)) can achieve better latency, throughput, reliability, and device utility than other parallel schedules. Also, the priority of the sub-module designs has been approved through the experiments.

关键词： parallel processing Task analysis Schedules Data models Training Pipelines Computational modeling Distributed learning system heterogeneity parallel inference hardware profiling task scheduling

来源：评论

学校读者我要写书评

暂无评论

HELIC-II - LEGAL REASONING SYSTEM ON THE parallel inference MACHINE

引用

NEW GENERATION COMPUTING 1993年第3-4期11卷 423-448页

作者： NITTA, K OHTAKE, Y MAEDA, S ONO, M OHSAKI, H SAKANE, K JAPAN INFORMAT PROC DEV CTR DEV & RES OFFTOKYOJAPAN NIPPON STEEL CORP LTD KITAKYUSHU 805JAPAN

This paper presents HELIC-II, a legal reasoning system on the parallel inference machine. HELIC-II draws legal conclusions for a given case by referring to a statutory law (legal rules) and judicial precedents (old cases). This system consists of two inference engines. The rule-based engine *** consequences logically by using legal rules. The case-based engine generates legal concepts by referencing similar old cases. These engines complementally draw all possible conclusions, and output them in the form of inference trees. Users can use these trees as material to construct arguments in a legal suit. HELIC-II is implemented on the parallel inference machine, and it can draw conclusions quickly by parallel inference. As an example, a legal inference system for the Penal Code is introduced, and the effectiveness of the legal reasoning and parallel inference model is shown.

关键词： LEGAL REASONING CASE-BASED REASONING ANALOGY parallel inference DEBATE NEGATION AS FAILURE THEOREM PROVER

来源：评论

学校读者我要写书评

暂无评论

parallel inference for cross-collection latent generalized Dirichlet allocation model and applications

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartA期238卷

作者： Luo, Zhiwen Amayri, Manar Fan, Wentao Ihou, Koffi Eddy Bouguila, Nizar Concordia Univ Concordia Inst Informat Syst Engn CIISE 1515 St Catherine St West Montreal PQ H3G 2W1 Canada Beijing Normal Univ Hong Kong Baptist Univ BNU HKB Guangdong Prov Key Lab IRADS Zhuhai 519088 Peoples R China Beijing Normal Univ Hong Kong Baptist Univ BNU HKB Dept Comp Sci Zhuhai 519088 Peoples R China

Existing cross-collection topic models with document-topic representation encounter performance bottlenecks in large-scale datasets due to their reliance on Dirichlet priors and conventional inference schemes. These constraints become noticeable in models derived from the Latent Dirichlet Allocation (LDA) framework. To address these challenges, this paper introduces the GPU-accelerated cross-collection latent generalized Dirichlet allocation (gccLGDA) model. This innovative approach integrates the benefits of generalized Dirichlet (GD) distribution with the computational prowess of GPU-based parallel inference, offering enhanced cross collection topic modeling. The gccLGDA employs the GD distribution presenting a more flexible prior with a comprehensive covariance structure, enabling a more nuanced capture of relationships between latent topics across different collections. Leveraging GPU for parallel inference, our model promises scalable and efficient training for expansive datasets, making it apt for large-scale data challenges. Through empirical evaluations in comparative text mining and document classification, we demonstrate the enhanced performance of the gccLGDA, highlighting its advantages over existing cross-collection topic models.

关键词： Cross-collection model Generalized Dirichlet parallel inference Graphics processing unit Topic correlation Comparative text mining

来源：评论

学校读者我要写书评

暂无评论

FastPTM: Fast weights loading of pre-trained models for parallel inference service provisioning

引用

parallel COMPUTING 2024年 122卷

作者： Cai, Fenglong Yuan, Dong Yang, Zhe Xu, Yonghui He, Wei Guo, Wei Cui, Lizhen Shandong Univ Sch Software 1500 Shunhua Rd Jinan 250101 Shandong Peoples R China Shandong Univ Joint SDU NTU Ctr Artificial Intelligence Res C FA 1500 Shunhua Rd Jinan 250101 Shandong Peoples R China Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia

Pre-trained models (PTMs) have demonstrated great success in a variety of NLP and CV tasks and have become a significant development in the field of deep learning. However, the large memory and high computational requirements associated with PTMs can increase the cost and time of inference, limiting their service provisioning in practical applications. To improve the Quality of Service (QoS) of PTM applications by reducing waiting and response times, we propose the FastPTM framework. This general framework aims to accelerate PTM inference services in a multi-tenant environment by reducing model loading time and switching overhead on GPUs. The framework utilizes a fast weights loading method based on weights and model separation of PTMs to efficiently accelerate parallel inference services in resource-constrained environments. Furthermore, an online scheduling algorithm is designed to reduce the inference service time. The results of the experiments indicate that FastPTM can improve the throughput of inference services by an average of 4x and up to 8.2x, while reducing the number of switches by 4.7x and the number of overtimes by 15.3x.

关键词： parallel inference Pre-trained models Service provisioning

来源：评论

学校读者我要写书评

暂无评论

parallel-inference Algorithms and Research of their Efficiency on Computer Systems

引用

SCIENTIFIC AND TECHNICAL INFORMATION PROCESSING 2018年第5期45卷 368-373页

作者： Vagin, V. N. Derevyanko, A. V. Kutepov, V. P. Moscow Power Engn Inst Dept Appl Math Moscow 111250 Russia

This article presents the results of research conducted on cluster systems with multicore nodes to create a method and an algorithm that implement parallel inference in the proof of formulas in first-order logic. The algorithm is based on of J. Robinson's resolution method of inference. A procedure for its parallelization, which allows one to dynamically control the uniform division of the set of resolvents distributed to the nodes of a computer system for inferring, is proposed. A number of heuristics, which make it possible to significantly reduce the time of implementing inference control decisions, are also introduced. Experiments here show that the effect on acceleration is higher than that of the previously studied parallel-inference algorithms.

关键词： parallel inference resolution principle parallel computing logic

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：