检索结果-内蒙古大学图书馆

ENAP: An Efficient Number-Aware Pruning Framework for Design Space Exploration of Approximate Configurations

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2023年第5期70卷 2062-2073页

作者： Dou, Yuqin Wang, Chenghua Woods, Roger Liu, Weiqiang Nanjing Univ Aeronaut & Astronaut NUAA Coll Elect & Informat Engn Nanjing 211106 Peoples R China Queens Univ Belfast Sch Elect Elect Engn & Comp Sci Belfast BT7 1NN North Ireland

Approximate computing has emerged as a new computing architecture paradigm that trades off necessary numerical accuracy for performance. Various approximation operation units such as adders and multipliers have been created and provide the basis for improving system efficiency, but it is clear, that a design space exploration (DSE) is needed if improved performance is to be systematically achieved. The challenge is to determine a suitable configuration among approximation units with different error characteristics to ensure a minimization of resources while not exceeding user-defined error constraints. In this paper, we propose the efficient number-aware pruning (ENAP) technique that can compress the search space size. Using common fault-tolerant applications, we demonstrate a compression rate up to 0.0008%, meaning that 99.9992% of invalid designs can remain unsearched. An improved genetic algorithm (GA) is subsequently proposed to improve ENAP, allowing the creation of the optimal configuration in only 2 to 3 iterations, thereby greatly improving search efficiency compared to the initial 9 iterations. We integrate these two approaches into the proposed framework, demonstrating how we can achieve better exploration results compared to state-of-the-artwork.

关键词： Space exploration Genetic algorithms Adders Approximate computing Energy consumption approximation algorithms Libraries design space exploration number-aware pruning genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Momentum-Accelerated Hessian-Vector-Based Latent Factor Analysis Model

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2023年第2期16卷 830-844页

作者： Li, Weiling Luo, Xin Yuan, Huaqiang Zhou, MengChu Dongguan Univ Technol Sch Comp Sci & Technol Dongguan 523808 Guangdong Peoples R China Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu 610054 Sichuan Peoples R China New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA Macau Univ Sci & Technol Macao Inst Syst Engn Collaborat Lab Intelligent Sci & Syst Macau 999078 Peoples R China

Service-oriented applications commonly involve high-dimensional and sparse (HiDS) interactions among users and service-related entities, e.g., user-item interactions from a personalized recommendation services system. How to perform precise and efficient representation learning on such HiDS interactions data is a hot yet thorny issue. An efficient approach to it is latent factor analysis (LFA), which commonly depends on large-scale non-convex optimization. Hence, it is vital to implement an LFA model able to approximate second-order stationary points efficiently for enhancing its representation learning ability. However, existing second-order LFA models suffer from high computational cost, which significantly reduces its practicability. To address this issue, this paper presents a Momentum-accelerated Hessian-vector algorithm (MH) for precise and efficient LFA on HiDS data. Its main ideas are two-fold: a) adopting the principle of a Hessian-vector-product-based method to utilize the second-order information without manipulating a Hessian matrix directly, and b) incorporating a generalized momentum method into its parameter learning scheme for accelerating its convergence rate to a stationary point. Experimental results on nine industrial datasets demonstrate that compared with state-of-the-art LFA models, an MH-based LFA model achieves gains in both accuracy and convergence rate. These positive outcomes also indicate that a generalized momentum method is compatible with the algorithms, e.g., a second-order algorithm, which implicitly rely on gradients.

关键词： Computational modeling approximation algorithms Convergence Analytical models Symbols Representation learning Optimization Services computing service application recommendation service high-dimensional and sparse data machine learning representation learning latent factor analysis hessian-vector second-order optimization generalized momentum method

来源：评论

学校读者我要写书评

暂无评论

Efficient Community Search in Edge-Attributed Graphs

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2023年第10期35卷 10790-10806页

作者： Li, Ling Zhao, Yuhai Luo, Siqiang Wang, Guoren Wang, Zhengkui Northeastern Univ Sch Comp Sci & Engn Minist Educ Shenyang 110819 Peoples R China Northeastern Univ Key Lab Intelligent Comp Med Image Minist Educ Shenyang 110819 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Beijing Inst Technol Sch Comp Sci & Technol Beijing 100081 Peoples R China Singapore Inst Technol InfoComm Technol Cluster Singapore 138683 Singapore

Given a graph, searching for a community containing a query vertex is a fundamental problem and has found many applications. Most existing community search models are based on non-attributed or vertex-attributed graphs. In many real-world graphs, however, the edges carry the richest information to describe the interactions between vertices;hence, it is important to take the information into account in community search. In this paper, we conduct a pioneer study on the community search on edge-attributed graphs. We proposed the Edge-Attributed Community Search (EACS) problem, which aims to extract a subgraph that contains the given query vertex while its edges have the maximum attribute similarity. We prove that the EACS problem is NP-hard and propose both exact and 2-approximation algorithms to address EACS. Our exact algorithms run up to 2320.34 times faster than the baseline solution. Our approximate algorithms further improve the efficiency by up to 2.93 times. We conducted extensive experiments to demonstrate the efficiency and effectiveness of our algorithms.

关键词： Artificial intelligence approximation algorithms Search problems Image edge detection Motion pictures Computer science Indexes Community search edge-attributed graphs

来源：评论

学校读者我要写书评

暂无评论

A New Elbow Estimation Method for Selecting the Best Solution in Sparse Unmixing

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 4328-4348页

作者： Sarjonen, Risto Raty, Tomi VTT Tech Res Ctr Finland Ltd Espoo 02044 Finland Microsoft Redmond WA 98052 USA

The goal of hyperspectral image analysis is often to determine which materials, out of a given set of possibilities, are present in each pixel. As hyperspectral data are being gathered in rapidly increasing amounts, automatic image analysis is becoming progressively more important. Automatic identification of materials from a mixed pixel is possible with 1) Bayesian unmixing algorithms and 2) multiobjective sparse unmixing algorithms when a method such as elbow estimation is used to select the best solution from the set of Pareto-optimal solutions. We develop a new elbow estimation method called termination condition adaptive elbow (TCAE) for selecting the best solution from the set of Pareto-optimal solutions to a biobjective unmixing problem. Specifically, the two objectives are assumed to be the sparsity level of the fractional abundance vector and the reconstruction error. We conduct experiments with real-world unmixing applications in mind, and TCAE performs significantly better than a state-of-the-art elbow estimation method when they are both used to select the best solution from the sequence of fractional abundance vectors generated by iterative spectral mixture analysis (ISMA). Furthermore, the combination of ISMA and TCAE is able to identify endmembers from mixed pixels several times faster and with higher F1-score than the two Bayesian unmixing algorithms used as a reference. We conclude that the combination of ISMA and TCAE facilitates automatic, reliable, and rapid identification of endmembers from mixed pixels.

关键词： Elbow Estimation Hyperspectral imaging Dictionaries Iterative algorithms Bayes methods approximation algorithms remote sensing sparse unmixing spectral mixture analysis

来源：评论

学校读者我要写书评

暂无评论

Kernel-Based Generalized Median Computation for Consensus Learning

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第5期45卷 5872-5888页

作者： Nienkoetter, Andreas Jiang, Xiaoyi Univ Munster Fac Math & Comp Sci D-48149 Munster Germany

Computing a consensus object from a set of given objects is a core problem in machine learning and pattern recognition. One popular approach is to formulate it as an optimization problem using the generalized median. Previous methods like the Prototype and Distance-Preserving Embedding methods transform objects into a vector space, solve the generalized median problem in this space, and inversely transform back into the original space. Both of these methods have been successfully applied to a wide range of object domains, where the generalized median problem has inherent high computational complexity (typically NP-hard) and therefore approximate solutions are required. Previously, explicit embedding methods were used in the computation, which often do not reflect the spatial relationship between objects exactly. In this work we introduce a kernel-based generalized median framework that is applicable to both positive definite and indefinite kernels. This framework computes the relationship between objects and its generalized median in kernel space, without the need of an explicit embedding. We show that the spatial relationship between objects is more accurately represented in kernel space than in an explicit vector space using easy-to-compute kernels, and demonstrate superior performance of generalized median computation on datasets of three different domains. A software toolbox resulting from our work is made publicly available to encourage other researchers to explore the generalized median computation and applications.

关键词： Kernel Transforms Three-dimensional displays Prototypes Euclidean distance approximation algorithms Software Consensus learning generalized median kernel functions distance-preserving embedding vector spaces

来源：评论

学校读者我要写书评

暂无评论

Adaptive CL-BFGS algorithms for Complex-Valued Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第9期34卷 6313-6327页

作者： Zhang, Yongliang Huang, He Shen, Gangxiang Soochow Univ Sch Elect & Informat Engn Suzhou 215006 Peoples R China Jiangsu Engn Res Ctr Novel Opt Fiber Technol & Co Suzhou 215006 Peoples R China

Complex-valued limited-memory BFGS (CL-BFGS) algorithm is efficient for the training of complex-valued neural networks (CVNNs). As an important parameter, the memory size represents the number of saved vector pairs and would essentially affect the performance of the algorithm. However, the determination of a suitable memory size for the CL-BFGS algorithm remains challenging. To deal with this issue, an adaptive method is proposed in which the memory size is allowed to vary during the iteration process. Basically, at each iteration, with the help of multistep quasi-Newton method, an appropriate memory size is chosen from a variable set {1,2,..., M} by approximating complex Hessian matrix as close as possible. To reduce the computational complexity and ensure desired performance, the upper bound M is adjustable according to the moving average of memory sizes found in previous iterations. The proposed adaptive CL-BFGS (ACL-BFGS) algorithm can be efficiently applied for the training of CVNNs. Moreover, it is suggested to take multiple memory sizes to construct the search direction, which further improves the performance of the ACL-BFGS algorithm. Experimental results on some benchmark problems including the pattern classification, complex function approximation, and nonlinear channel equalization problems are given to illustrate the advantages of the developed algorithms over some previous ones.

关键词： approximation algorithms Training Signal processing algorithms Optimization Neural networks Upper bound Mathematical models Adaptive complex-valued limited-memory BFGS (ACL-BFGS) algorithm complex-valued neural networks (CVNNs) moving average multistep quasi-Newton method variable memory size

来源：评论

学校读者我要写书评

暂无评论

Distributed Actor-Critic algorithms for Multiagent Reinforcement Learning Over Directed Graphs

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第10期34卷 7210-7221页

作者： Dai, Pengcheng Yu, Wenwu Wang, He Baldi, Simone Southeast Univ Sch Math Nanjing 210096 Peoples R China Southeast Univ Sch Automat Nanjing 210096 Peoples R China Delft Univ Technol Delft Ctr Syst & Control NL-2628 CD Delft Netherlands

Actor-critic (AC) cooperative multiagent reinforcement learning (MARL) over directed graphs is studied in this article. The goal of the agents in MARL is to maximize the globally averaged return in a distributed way, i.e., each agent can only exchange information with its neighboring agents. AC methods proposed in the literature require the communication graphs to be undirected and the weight matrices to be doubly stochastic (more precisely, the weight matrices are row stochastic and their expectation are column stochastic). Differently from these methods, we propose a distributed AC algorithm for MARL over directed graph with fixed topology that only requires the weight matrix to be row stochastic. Then, we also study the MARL over directed graphs (possibly not connected) with changing topologies, proposing a different distributed AC algorithm based on the push-sum protocol that only requires the weight matrices to be column stochastic. Convergence of the proposed algorithms is proven for linear function approximation of the action value function. Simulations are presented to demonstrate the effectiveness of the proposed algorithms.

关键词： Directed graphs Topology approximation algorithms Convergence Protocols Q-learning Function approximation Directed graph distributed actor-critic (AC) algorithm multiagent reinforcement learning (MARL) push-sum protocol

来源：评论

学校读者我要写书评

暂无评论

Robust Losses for Learning Value Functions

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第5期45卷 6157-6167页

作者： Patterson, Andrew Liao, Victor White, Martha Univ Alberta Comp Sci Edmonton AB T6G 2R3 Canada Univ Waterloo Fac Math Waterloo ON N2L 3G1 Canada

Most value function learning algorithms in reinforcement learning are based on the mean squared (projected) Bellman error. However, squared errors are known to be sensitive to outliers, both skewing the solution of the objective and resulting in high-magnitude and high-variance gradients. To control these high-magnitude updates, typical strategies in RL involve clipping gradients, clipping rewards, rescaling rewards, or clipping errors. While these strategies appear to be related to robust losses-like the Huber loss-they are built on semi-gradient update rules which do not minimize a known loss. In this work, we build on recent insights reformulating squared Bellman errors as a saddlepoint optimization problem and propose a saddlepoint reformulation for a Huber Bellman error and Absolute Bellman error. We start from a formalization of robust losses, then derive sound gradient-based approaches to minimize these losses in both the online off-policy prediction and control settings. We characterize the solutions of the robust losses, providing insight into the problem settings where the robust losses define notably better solutions than the mean squared Bellman error. Finally, we show that the resulting gradient-based algorithms are more stable, for both prediction and control, with less sensitivity to meta-parameters.

关键词： approximation algorithms Optimization Function approximation Prediction algorithms Visualization Tuning Time-frequency analysis Machine learning reinforcement learning function approximation

来源：评论

学校读者我要写书评

暂无评论

How Do You Want Your Greedy: Simultaneous or Repeated?

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2023年第1期24卷 1-87页

作者： Feldman, Moran Harshaw, Christopher Karbasi, Amin Univ Haifa Dept Comp Sci Haifa Israel Univ Calif Berkeley Simons Inst Berkeley CA USA Yale Univ Dept Elect Engeering New Haven CT USA Yale Univ Dept Comp Sci New Haven CT USA Yale Univ Dept Stat & Data Sci New Haven CT USA

We present SIMULTANEOUSGREEDYS, a deterministic algorithm for constrained submodular maximization. At a high level, the algorithm maintains l solutions and greedily updates them in a simultaneous fashion. SIMULTANEOUSGREEDYS achieves the tightest known which are (k + 1)2/k = k + O(1) and (1 + root k + 2)2 = k + O( approximation guarantees for both k-extendible systems and the more general k-systems, root k), respectively. We also improve the analysis of REPEATEDGREEDY, showing that it achieves an approximation root root ratio of k+O( k) for k-systems when allowed to run for O( k) iterations, an improvement in both the runtime and approximation over previous analyses. We demonstrate that both algorithms may be modified to run in nearly linear time with an arbitrarily small loss in the approximation. Both SIMULTANEOUSGREEDYS and REPEATEDGREEDY are flexible enough to incor-porate the intersection of m additional knapsack constraints, while retaining similar ap-proximation guarantees: both algorithms yield an approximation guarantee of roughly k + 2m + O(root k + m) for k-systems and SIMULTANEOUSGREEDYS enjoys an improved ap-proximation guarantee of k + 2m + O(root m) for k-extendible systems. To complement our algorithmic contributions, we prove that no algorithm making polynomially many oracle queries can achieve an approximation better than k + 1/2 - epsilon. We also present ***, a Julia package which implements these algorithms. Finally, we test these algorithms on real datasets.

关键词： Submodular maximization k-systems k-extendible systems approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Service Home Identification of Multiple-Source IoT Applications in Edge Computing

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2023年第2期16卷 1417-1430页

作者： Li, Jing Liang, Weifa Xu, Wenzheng Xu, Zichuan Li, Yuchen Jia, Xiaohua Australian Natl Univ Sch Comp Canberra ACT 2601 Australia City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Sichuan Univ Coll Comp Sci Chengdu 610017 Peoples R China Dalian Univ Technol Sch Software Dalian 116024 Peoples R China

The real-time communication requirement of the Internet of Things (IoT) applications promotes the convergence of IoT and Mobile Edge Computing (MEC). The MEC paradigm greatly shortens the IoT service delay by leveraging cloudlets (edge servers) of MEC in the proximity of IoT devices. Considering limited computing and storage resources in an MEC network, it is challenging to provide efficient IoT-enabled service provisioning in such a network. In this article, we study the service home identification problem of service provisioning for multi-source IoT applications in an MEC network, by identifying a service home (cloudlet) of each multi-source IoT application for its data processing, querying and storage. Each multi-source IoT application consists of multiple sources located at different geographical locations and each source uploads its data stream via a gateway (its nearby access point) to the MEC network and the uploaded data then is aggregated with the stream data of the other sources of the IoT application at the service home. We here focus on two novel service home identification problems: the service operational cost minimization problem with the aim to minimize the total service operational cost by admitting as many multi-source IoT applications as possible, and the online throughput maximization problem with the aim to maximize the number of multi-source IoT application requests admitted. We first show that both the problems are NP-hard. We then formulate an Integer Linear Programming (ILP) solution to the service operational cost minimization problem, and propose a randomized algorithm with high probability and a deterministic approximation algorithm respectively, at moderate resource capacity violations. We third develop an efficient heuristic algorithm for the problem without any resource violation. Furthermore, we deal with the online throughput maximization problem under an assumption that multi-source IoT application requests arrive one by one without

关键词： Internet of Things Heuristic algorithms Cloud computing Costs approximation algorithms Minimization Delays Internet of Things (IoT) mobile edge computing (MEC) service provisioning for multi-source IoT applications service operational cost minimization randomized algorithm online algorithm resource allocation and optimization dynamic IoT application request admissions network slicing in edge computing

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：