检索结果-内蒙古大学图书馆

decentralized Dictionary Learning Over Time-Varying Digraphs

JOURNAL OF MACHINE LEARNING RESEARCH 2019年第1期20卷 1-62页

作者： Daneshmand, Amir Sun, Ying Scutari, Gesualdo Facchinei, Francisco Sadler, Brian M. Purdue Univ Sch Ind Engn W Lafayette IN 47907 USA Univ Roma La Sapienza Dept Comp Control & Management Engn Rome Italy US Army Res Lab Adelphi MD USA

This paper studies Dictionary Learning problems wherein the learning task is distributed over a multi-agent network, modeled as a time-varying directed graph. This formulation is relevant, for instance, in Big Data scenarios where massive amounts of data are collected/stored in different locations (e.g., sensors, clouds) and aggregating and/or processing all data in a fusion center might be inefficient or unfeasible, due to resource limitations, communication overheads or privacy issues. We develop a unified decentralized algorithmic framework for this class of nonconvex problems, which is proved to converge to stationary solutions at a sublinear rate. The new method hinges on Successive Convex Approximation techniques, coupled with a decentralized tracking mechanism aiming at locally estimating the gradient of the smooth part of the sum-utility. To the best of our knowledge, this is the first provably convergent decentralized algorithm for Dictionary Learning and, more generally, bi-convex problems over (time-varying) (di)graphs.

关键词： decentralized algorithms dictionary learning directed graph non-convex optimization time-varying network

来源：评论

学校读者我要写书评

暂无评论

decentralized Generalized Approximate Message-Passing for Tree-Structured Networks

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2024年第10期70卷 7385-7409页

作者： Takeuchi, Keigo Toyohashi Univ Technol Dept Elect & Elect Informat Engn Toyohashi 4418580 Japan

decentralized generalized approximate message-passing (GAMP) is proposed for compressed sensing from distributed generalized linear measurements in a tree-structured network. Consensus propagation is used to realize average consensus required in GAMP via local communications between adjacent nodes. decentralized GAMP is applicable to all tree-structured networks that do not necessarily have central nodes connected to all other nodes. State evolution is used to analyze the asymptotic dynamics of decentralized GAMP for zero-mean independent and identically distributed Gaussian sensing matrices. The state evolution recursion for decentralized GAMP is proved to have the same fixed points as that for centralized GAMP when homogeneous measurements with an identical dimension in all nodes are considered. Furthermore, existing long-memory proof strategy is used to prove that the state evolution recursion for decentralized GAMP with the Bayes-optimal denoisers converges to a fixed point. These results imply that the state evolution recursion for decentralized GAMP with the Bayes-optimal denoisers converges to the Bayes-optimal fixed point for the homogeneous measurements when the fixed point is unique. Numerical results for decentralized GAMP are presented in the cases of linear measurements and clipping. As examples of tree-structured networks, a one-dimensional chain and a tree with no central nodes are considered.

关键词： Bayes methods Distributed algorithms Ad hoc networks Convergence Sensors Symmetric matrices Signal processing algorithms Compressed sensing generalized approximate message-passing decentralized algorithms consensus propagation tree-structured networks state evolution

来源：评论

学校读者我要写书评

暂无评论

Loss-cognizant pricing in networks with greedy users

引用

COMPUTER NETWORKS 2007年第6期51卷 1660-1683页

作者： Al Daoud, Ashraf Alanyali, Murat Boston Univ Dept Elect & Comp Engn Boston MA 02215 USA Boston Univ Ctr Informat Syst & Engn Boston MA 02215 USA

We consider link pricing in packet-switched networks with fixed routing and random congestion losses. Network users are assumed to be greedy in the sense that each user increases its traffic rate in proportion to profit per packet it generates. The main goal of the paper is to devise pricing principles that maximize social welfare, which is taken as either the sum of goodputs or the sum of log-goodputs in the network. We adopt a deterministic fluid model whose analysis leads to pricing policies that stabilize packet generation rates at local maxima of social welfare for a rich set of network topologies. We also give decentralized algorithms to compute the price of packet forwarding at each link. Neither computation nor implementation of prices requires per-flow information. Obtained analytical results are verified via packet level simulations. (c) 2006 Elsevier B.V. All rights reserved.

关键词： pricing congestion losses non-cooperative sessions social welfare maximization fluid models decentralized algorithms

来源：评论

学校读者我要写书评

暂无评论

decentralized Perimeter Surveillance Using a Team of UAVs

引用

IEEE TRANSACTIONS ON ROBOTICS 2008年第6期24卷 1394-1404页

作者： Kingston, Derek Beard, Randal W. Holt, Ryan S. USAF Res Lab Wright Patterson AFB OH 45433 USA Brigham Young Univ Dept Elect & Comp Engn Provo UT 84602 USA MIT Lincoln Lab Lexington MA 02421 USA

This paper poses the cooperative perimeter-surveillance problem and offers a decentralized solution that accounts for perimeter growth (expanding or contracting) and insertion/deletion of team members. By identifying and sharing the critical coordination information and by exploiting the known communication topology, only a small communication range is required for accurate performance. Simulation and hardware results are presented that demonstrate the applicability of the solution.

关键词： Cooperative control coordination variables decentralized algorithms perimeter surveillance small unmanned aerial vehicles (UAVs)

来源：评论

学校读者我要写书评

暂无评论

decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2021年第1期22卷 1-69页

作者： Gurbuzbalaban, Mert Gao, Xuefeng Hu, Yuanhan Zhu, Lingjiong Rutgers Business Sch Dept Management Sci & Informat Syst Piscataway NJ 08854 USA Chinese Univ Hong Kong Dept Syst Engn & Engn Management Shatin NT Hong Kong Peoples R China Florida State Univ Dept Math Tallahassee FL 32306 USA

Stochastic gradient Langevin dynamics (SGLD) and stochastic gradient Hamiltonian Monte Carlo (SGHMC) are two popular Markov Chain Monte Carlo (MCMC) algorithms for Bayesian inference that can scale to large datasets, allowing to sample from the posterior distribution of the parameters of a statistical model given the input data and the prior distribution over the model parameters. However, these algorithms do not apply to the decentralized learning setting, when a network of agents are working collaboratively to learn the parameters of a statistical model without sharing their individual data due to privacy reasons or communication constraints. We study two algorithms: decentralized SGLD (DE-SGLD) and decentralized SGHMC (DE-SGHMC) which are adaptations of SGLD and SGHMC methods that allow scaleable Bayesian inference in the decentralized setting for large datasets. We show that when the posterior distribution is strongly log-concave and smooth, the iterates of these algorithms converge linearly to a neighborhood of the target distribution in the 2-Wasserstein distance if their parameters are selected appropriately. We illustrate the efficiency of our algorithms on decentralized Bayesian linear regression and Bayesian logistic regression problems.

关键词： Langevin dynamics Hamiltonian Monte Carlo decentralized algorithms decentralized Bayesian inference stochastic gradient momentum acceleration Heavy-ball method convergence rate Wasserstein distance

来源：评论

学校读者我要写书评

暂无评论

The Sensor-based Random Graph Method for Cooperative Robot Exploration

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2009年第2期14卷 163-175页

作者： Franchi, Antonio Freda, Luigi Oriolo, Giuseppe Vendittelli, Marilena Univ Roma La Sapienza Dipartimento Informat & Sistemist I-00185 Rome Italy

We present a decentralized cooperative exploration strategy for a team of mobile robots equipped with range finders. A roadmap of the explored area, with the associate safe region, is built in the form of a sensor-based random graph (SRG). This is expanded by the robots by using a randomized local planner that automatically realizes a tradeoff between information gain and navigation cost. The nodes of the SRG represent view configurations that have been visited by at least one robot, and are connected by arcs that represent safe paths. These paths have been actually traveled by the robots or added to the SRG to improve its connectivity. decentralized cooperation and coordination mechanisms are used so as to guarantee exploration efficiency and avoid conflicts. Simulations and experiments are presented to show the performance of the proposed technique.

关键词： Cooperative exploration decentralized algorithms multirobot systems

来源：评论

学校读者我要写书评

暂无评论

OMP Based Joint Sparsity Pattern Recovery Under Communication Constraints

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2014年第19期62卷 5059-5072页

作者： Wimalajeewa, Thakshila Varshney, Pramod K. Syracuse Univ Dept Elect Engn & Comp Sci Syracuse NY 13244 USA

We address the problem of joint sparsity pattern recovery based on multiple measurement vectors (MMVs) in resource constrained distributed networks. We assume that distributed nodes observe sparse signals that share a common (but unknown) sparsity pattern. Each node is assumed to sample the sparse signals via different sensing matrices in general. In many distributed communication networks, it is often required that joint sparse recovery be performed under inherent resource constraints such as communication bandwidth and transmit/processing power. We propose two approaches to take the communication constraints into account while performing joint sparsity pattern recovery. First, we explore the use of a shared multiple access channel (MAC) in forwarding observation vectors from each node to a fusion center. With MAC, while the bandwidth requirement does not depend on the number of nodes, the fusion center has access to only linear combinations of the observations. We discuss the conditions under which the common sparsity pattern can be recovered reliably. Second, we develop two efficient collaborative algorithms based on orthogonal matching pursuit (OMP), to jointly estimate the common sparsity pattern in a decentralized manner with a low communication overhead. In the proposed algorithms, each node collaborates with neighboring nodes by sharing a small amount of information at different stages while estimating the indices of the true sparsity pattern in a greedy manner. The tradeoff between the performance gain and the communication overhead of the proposed algorithms is demonstrated via simulations.

关键词： Multiple measurement vectors (MMVs) sparsity pattern recovery compressive sensing orthogonal matching pursuit (OMP) decentralized algorithms

来源：评论

学校读者我要写书评

暂无评论

SPARQ-SGD: Event-Triggered and Compressed Communication in decentralized Optimization

引用

IEEE TRANSACTIONS ON AUTOMATIC CONTROL 2023年第2期68卷 721-736页

作者： Singh, Navjot Data, Deepesh George, Jemin Diggavi, Suhas Univ Calif Los Angeles Dept Elect & Comp Engn Los Angeles CA 90095 USA US Army Res Lab Adelphi MD 20783 USA

In this article, we propose and analyze SParsified Action Regulated Quantized-Stochastic Gradient Descent (SPARQ-SGD), a communication-efficient algorithm for decentralized training of large-scale machine learning models over a graph with $n$ nodes, where communication efficiency is achieved using compressed exchange of local model parameters among neighboring nodes, which is triggered only when an event (a locally computable condition) is satisfied. Specifically, in SPARQ-SGD, each node takes a fixed number of local gradient steps and then checks if the model parameters have significantly changed compared to its last update;only when the change is beyond a certain threshold (specified by a design criterion), it compresses its local model parameters using both quantization and sparsification and communicates them to its neighbors. We prove that SPARQ-SGD converges as O(1/nT) and O(1/root nT) in the strongly convex and nonconvex settings, respectively, matching the convergence rates of plain decentralized SGD. This demonstrates that we get communication efficiency achieved by aggressive compression, local iterations, and event-triggered communication essentially for free. We evaluate SPARQ-SGD over real datasets to demonstrate significant amount of savings in communication over the state-of-the-art while achieving similar performance.

关键词： Consensus convergence decentralized algorithms efficient-communication event-triggered mul-tiagent systems stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

Max-Min Fairness in 802.11 Mesh Networks

引用

IEEE-ACM TRANSACTIONS ON NETWORKING 2012年第3期20卷 756-769页

作者： Leith, Douglas J. Cao, Qizhi Subramanian, Vijay G. NUI Maynooth Hamilton Inst Maynooth Kildare Ireland

In this paper, we establish that the rate region of a large class of IEEE 802.11 mesh networks is log-convex, immediately allowing standard utility fairness methods to be generalized to this class of networks. This creates a solid theoretical underpinning for fairness analysis and resource allocation in this practically important class of networks. For the special case of max-min fairness, we use this new insight to obtain an almost complete characterization of the fair rate allocation and a remarkably simple, practically implementable method for achieving max-min fairness in 802.11 mesh networks.

关键词： 802.11 decentralized algorithms max-min fairness mesh networks TXOP utility fairness WLANs

来源：评论

学校读者我要写书评

暂无评论

Optimal Web cache sizing: scalable methods for exact solutions

引用

COMPUTER COMMUNICATIONS 2001年第2期24卷 163-173页

作者： Kelly, T Reeves, D Univ Michigan Dept Elect Engn & Comp Sci Ann Arbor MI 48109 USA

This paper describes two approaches to the problem of determining exact optimal storage capacity for Web caches based on expected workload and the monetary costs of memory and bandwidth. The first approach considers memory/bandwidth tradeoffs in an idealized model. It assumes that workload consists of independent references drawn from a known distribution (e.g. Zipf) and caches employ a "Perfect LFU" removal policy. We derive conditions under which a shared higher-level "parent" cache serving several lower-level "child" caches is economically viable. We also characterize circumstances under which globally optimal storage capacities in such a hierarchy can be determined through a decentralized computation in which caches individually minimize local monetary expenditures. The second approach is applicable if the workload at a single cache is represented by an explicit request sequence and the cache employs any one of a large family of removal policies that includes LRU. The miss costs associated with individual requests may be completely arbitrary, and the cost of cache storage need only be monotonic. We use an efficient single-pass simulation algorithm to compute aggregate miss cost as a function of cache size in O(M log M) time and O(M) memory, where M is the number of requests in the workload. Because it allows us to compute arbitrarily weighted hit rates at all cache sizes with modest computational resources, this algorithm permits us to measure cache performance with no loss of precision. The same basic algorithm also permits us to compute complete stack distance transformations in O(M log N) time and O(N) memory, where N is the number of unique items referenced. Experiments on very large reference streams show that our algorithm computes stack distances more quickly than several alternative approaches, demonstrating that it is a useful tool for measuring temporal locality in cache workloads. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： Web caches memory bandwidth capacity planning LRV stack distance stack algorithms optimisation economic approaches decentralized algorithms

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：