检索结果-内蒙古大学图书馆

Variance-Reduced Stochastic Quasi-Newton Methods for Decentralized Learning

IEEE TRANSACTIONS ON signal processing 2023年 71卷 311-326页

作者： Zhang, Jiaojiao Liu, Huikang So, Anthony Man-Cho Ling, Qing KTH Royal Inst Technol Div Decis & Control Syst S-11428 Stockholm Sweden Shanghai Univ Finance & Econ Sch Informat Management & Engn Shanghai 200437 Peoples R China Chinese Univ Hong Kong Dept Syst Engn & Engn Management Shatin Hong Kong Peoples R China Sun Yat Sen Univ Sch Comp Sci & Engn Guangdong Prov Key Lab Computat Sci Guangzhou 510006 Guangdong Peoples R China Pazhou Lab Guangzhou 510300 Guangdong Peoples R China

In this work, we investigate stochastic quasi-Newton methods for minimizing a finite sum of cost functions over a decentralized network. We first develop a general algorithmic framework, in which each node constructs a local, inexact quasi-Newton direction that asymptotically approaches the global, exact one at each time step. To do so, a local gradient approximation is constructed using dynamic average consensus to track the average of variance-reduced local stochastic gradients over the entire network, followed by a proper local Hessian inverse approximation. We show that under standard convexity and smoothness assumptions on the cost functions, the methods obtained from our framework converge linearly to the optimal solution if the local Hessian inverse approximations used have uniformly bounded positive eigenvalues. To construct the Hessian inverse approximations with the said boundedness property, we design two fully decentralized stochastic quasi-Newton methods-namely, the damped regularized limited-memory DFP (Davidon-Fletcher-Powell) and the damped limited-memory BFGS (Broyden-Fletcher-Goldfarb-Shanno)-which use a fixed moving window of past local gradient approximations and local decision variables to adaptively construct Hessian inverse approximations. A noteworthy feature of these methods is that they do not require extra sampling or communication. Numerical results show that the proposed decentralized stochastic quasi-Newton methods are much faster than the existing decentralized stochastic first-order algorithms.

关键词： Costs Convergence signal processing algorithms Approximation algorithms Cost function Newton method Computational complexity Decentralized optimization stochastic quasi-Newton methods variance reduction damped limited-memory DFP damped limited-memory BFGS

来源：评论

学校读者我要写书评

暂无评论

Cramr-Rao Bounds of Near-Field Positioning Based on Electromagnetic Propagation Model

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2023年第11期72卷 13808-13825页

作者： Chen, Ang Chen, Li Chen, Yunfei You, Changsheng Wei, Guo Yu, F. Richard Univ Sci & Technol China CAS Key Lab Wireless Opt Commun Hefei 230027 Peoples R China Univ Durham Dept Engn Durham DH1 3LE England Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen 518055 Peoples R China Carleton Univ Dept Syst & Comp Engn Ottawa ON K1S 5B6 Canada

The adoption of large-scale antenna arrays at highfrequency bands is widely envisioned in the beyond 5G wireless networks. This leads to the near-field regime where the wavefront is no longer planar but spherical, bringing new opportunities and challenges for communications and positioning. In this article, we improve the near-field positioning technology from the classical spherical wavefront model (SWM) to the more accurate and true electromagnetic propagation model (EPM). A generic near-field positioning model with different observation capabilities for three electric field types (vector, scalar, and overall scalar electric field) is developed based on the complete EPM. For these three observed electric field types, the Cramer-Rao bound (CRB) is adopted to evaluate the achievable estimation accuracy. The expressions of the CRBs for different electric field observations are derived by combining electromagnetic propagation concepts with estimation theory. Closed-form expressions can be further obtained as the terminal is assumed to be on the central perpendicular line (CPL) of the receiving antenna surface. Moreover, the above discussions are extended to the system with multiple receiving antennas. In this case, the CRBs using various electric field types are derived and the effect of different numbers of receiving antennas is deeply investigated. Numerical results are provided to quantify the CRBs and validate the analytical results. Also, the impact of different system parameters, including electric field type, wavelength, size of the receiving antenna, and number of antennas, is evaluated.

关键词： Receiving antennas Electric fields Estimation signal processing algorithms Antenna measurements Linear antenna arrays Analytical models Cramer-Rao bound electromagnetic propagation model electric fields multiple antennas generic near-field positioning observation capability performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Joint Maximum Likelihood Estimation of Microphone Array Parameters for a Reverberant Single Source Scenario

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE processing 2023年 31卷 695-705页

作者： Li, Changheng Martinez, Jorge Hendriks, Richard Christian Delft Univ Technol Fac Elect Engn Math & Comp Sci NL-2628 CD Delft Netherlands

Estimation of the acoustic-scene related parameters such as relative transfer functions (RTFs) from source to microphones, source power spectral densities (PSDs) and PSDs of the late reverberation is essential and also challenging. Existing maximum likelihood estimators typically consider only subsets of these parameters and use each time frame separately. In this paper we explicitly focus on the single source scenario and first propose a joint maximum likelihood estimator (MLE) to estimate all parameters jointly using a single time frame. Since the RTFs are typically invariant for a number of consecutive time frames we also propose a joint maximum likelihood estimator (MLE) using multiple time frames which has similar estimation performance compared to a recently proposed reference algorithm called simultaneously confirmatory factor analysis (SCFA), but at a much lower complexity. Moreover, we present experimental results which demonstrate that the estimation accuracy, together with the performance of noise reduction, speech quality and speech intelligibility, of our proposed joint MLE outperform those of existing MLE based approaches that use only a single time frame.

关键词： Maximum likelihood estimation Array signal processing Noise reduction Transfer functions signal processing algorithms Parallel processing Microphone arrays Dereverberation maximum likelihood estima- tion microphone array signal processing PSD estimation RTF estimation

来源：评论

学校读者我要写书评

暂无评论

Metalearning-Based Alternating Minimization Algorithm for Nonconvex Optimization

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第9期34卷 5366-5380页

作者： Xia, Jing-Yuan Li, Shengxi Huang, Jun-Jie Yang, Zhixiong Jaimoukha, Imad M. Gunduz, Deniz Natl Univ Def Technol Coll Elect Engn Coll Comp Changsha 410073 Peoples R China Beihang Univ Coll Elect Engn Beijing 100191 Peoples R China Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England Univ Modena & Reggio Emilia UNIMORE Dept Engn Enzo Ferrari I-41121 Modena Italy

In this article, we propose a novel solution for nonconvex problems of multiple variables, especially for those typically solved by an alternating minimization (AM) strategy that splits the original optimization problem into a set of subproblems corresponding to each variable and then iteratively optimizes each subproblem using a fixed updating rule. However, due to the intrinsic nonconvexity of the original optimization problem, the optimization can be trapped into a spurious local minimum even when each subproblem can be optimally solved at each iteration. Meanwhile, learning-based approaches, such as deep unfolding algorithms, have gained popularity for nonconvex optimization;however, they are highly limited by the availability of labeled data and insufficient explainability. To tackle these issues, we propose a meta-learning based alternating minimization (MLAM) method that aims to minimize a part of the global losses over iterations instead of carrying minimization on each subproblem, and it tends to learn an adaptive strategy to replace the handcrafted counterpart resulting in advance on superior performance. The proposed MLAM maintains the original algorithmic principle, providing certain interpretability. We evaluate the proposed method on two representative problems, namely, bilinear inverse problem: matrix completion and nonlinear problem: Gaussian mixture models. The experimental results validate the proposed approach outperforms AM-based methods.

关键词： Optimization Minimization Task analysis Deep learning Neural networks signal processing algorithms Iterative algorithms Alternating minimization (AM) deep unfolding gaussian mixture model (GMM) matrix completion meta-learning (ML)

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution With Binary Priors: Theory and algorithms

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 3213-3228页

作者： Sarangi, Pulak Hattori, Ryoma Komiyama, Takaki Pal, Piya Univ Calif San Diego Elect & Comp Engn La Jolla CA 92092 USA Univ Calif San Diego Ctr Neural Circuits & Behav Neurobiol Sect Dept Neurosci La Jolla CA 92092 USA Univ Calif Halicioglu Data Sci Inst San Diego CA 92092 USA

The problem of super-resolution is concerned with the reconstruction of temporally/spatially localized events (or spikes) from samples of their convolution with a low-pass filter. Distinct from prior works which exploit sparsity in appropriate domains in order to solve the resulting ill-posed problem, this paper explores the role of binary priors in super-resolution, where the spike (or source) amplitudes are assumed to be binary-valued. Our study is inspired by the problem of neural spike deconvolution, but also applies to other applications such as symbol detection in hybrid millimeter wave communication systems. This paper makes several theoretical and algorithmic contributions to enable binary super-resolution with very few measurements. Our results show that binary constraints offer much stronger identifiability guarantees than sparsity, allowing us to operate in "extreme compression" regimes, where the number of measurements can be significantly smaller than the sparsity level of the spikes. To ensure exact recovery in this "extreme compression" regime, it becomes necessary to design algorithms that exactly enforce binary constraints without relaxation. In order to overcome the ensuing computational challenges, we consider a first order auto-regressive filter (which appears in neural spike deconvolution), and exploit its special structure. This results in a novel formulation of the super-resolution binary spike recovery in terms of binary search in one dimension. We perform numerical experiments that validate our theory and also show the benefits of binary constraints in neural spike deconvolution from real calcium imaging datasets.

关键词： Superresolution Deconvolution Filtering algorithms Calcium Low-pass filters IIR filters signal processing algorithms Beta-expansions binary compressed sensing sparsity binary search spike deconvolution super-resolution

来源：评论

学校读者我要写书评

暂无评论

Scalable Distributed Data-Driven State Estimation Algorithm via Gaussian Processes With Guaranteed Stability

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2023年第6期59卷 9191-9204页

作者： Yu, Xingkai Sun, Xianzheng Li, Jianxun North China Elect Power Univ Sch Control & Comp Engn Beijing 102206 Peoples R China Tsinghua Univ Dept Precis Instrument Beijing 100084 Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China

In this article, we focus on the scalable distributed data-driven state estimation problem using Gaussian processes (GPs). The framework includes two parts: 1) the data-driven training approach and 2) the state-estimation architecture. First, the objective is to obtain the transition and measurement functions of the considered state-space model by a data-driven training strategy via distributed GPs. In particular, to improve the training efficiency, we employ an online conditioning algorithm, which reduces the computational burden significantly. Then, all nodes exchange their own trained GPs with their respective neighbors. Furthermore, to achieve consensus on local trained GPs, we propose a Wasserstein weighted average consensus algorithm, which differs from the current Kullback-Leibler average consensus on probability densities. Second, based on the training results, we propose a distributed state estimation algorithm to perform fresh state estimation. After obtaining the state estimation results (mean and covariance) and exchanging them with their neighboring nodes, we then execute the Wasserstein weighted average to achieve consensus on state estimations. Also, we analyze the stability and robustness of the proposed distributed state estimation by using GP. Finally, numerical and real-world examples are provided to validate the effectiveness of the proposed training method and data-driven state estimation algorithms.

关键词： State estimation Training Kernel Mathematical models signal processing algorithms Interpolation Gaussian processes Data-driven distributed state estimation Gaussian processes (GPs) stability analysis Wasserstein average consensus

来源：评论

学校读者我要写书评

暂无评论

Passive Tone Detection for Moving Targets Based on Long-Time Coherent Integration

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 2023年第3期48卷 820-836页

作者： Zhang, Liu Piao, Shengchun Guo, Junyuan Wang, Xiaohan Harbin Engn Univ Coll Underwater Acoust Engn Harbin 150001 Peoples R China Harbin Engn Univ Acoust Sci & Technol Lab Harbin 150001 Peoples R China Harbin Engn Univ Key Lab Marine Informat Acquisit & Secur Minist Ind & Informat Technol Harbin 150001 Peoples R China Harbin Engn Univ Coll Underwater Acoust Engn Harbin 150001 Peoples R China

The detection of sinusoidal signals embedded in noise is an important topic in passive sonar signal processing. The performance of existing tone detection techniques is limited by the Doppler frequency shift, which is caused by the relative motion between moving targets and the receiver. In this study, an algorithm based on long-time coherent integration is proposed to achieve robust tonal signal detection under the influence of a Doppler frequency shift. First, the received narrowband signals radiated by moving targets are split into multiple segments through a window-length constraint. The results obtained by applying a discrete Fourier transform (DFT) to the data segments are modeled as a polynomial phase signal in the frequency domain. Then, the polynomial Radon-polynomial Fourier transform (PRPFT) is applied to simultaneously compensate the time-variant frequency drift and phase difference. To avoid the gain loss due to the discretization of the phase difference compensation in PRPFT, a phase compensation factor searching algorithm is proposed. The simulation results show that the proposed algorithm can provide higher frequency resolution and higher coherent integration gain even in the case of a severe Doppler shift. Furthermore, the results of sea trials demonstrate that the proposed method can perfectly achieve coherent integration for signals with a duration of several hundred seconds under different experimental conditions.

关键词： Detectors signal processing algorithms Time-frequency analysis Discrete Fourier transforms Estimation signal to noise ratio signal resolution Long-time coherent integration moving target passive tone detection

来源：评论

学校读者我要写书评

暂无评论

Density-Based Affinity Propagation Tensor Clustering for Intelligent Fault Diagnosis of Train Bogie Bearing

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第6期24卷 6053-6064页

作者： Wei, Zexian He, Deqiang Jin, Zhenzhen Liu, Bin Shan, Sheng Chen, Yanjun Miao, Jian Guangxi Univ Sch Mech Engn Guangxi Key Lab Mfg Syst & Adv Mfg Technol Nanning 530004 Peoples R China Guangxi Univ Sch Elect Engn Nanning 530004 Peoples R China Zhuzhou CRRC Times Elect Co Ltd Zhuzhou 412001 Peoples R China

Health monitor of bogie-bearing on the train can ensure constant operation of the rail transit system. Since the metro or other rail transit have high safety requirements, it is hard to acquire numerous fault samples. Besides, diagnosing train bogie-bearings under variable working conditions is challenging due to wheel-rail coupling, speed variation, and load fluctuation. An intelligent approach for bogie-bearing fault diagnosis is proposed to deal with the above problems. A third-order tensor model is established to be suitable for variable working conditions. Furthermore, a density-based affinity propagation tensor (DAP-Tensor) clustering algorithm is presented to identify different failures with unlabeled. Train bogie and public data sets were employed to simulate three probable conditions of train operation: high-frequency impact, speed variation, and load change. Compared with existing clustering methods in three cases, the proposed DAP-Tensor performs better in identifying bearing faults under variable working conditions. Moreover, The DAP-tensor has a comparable recognition rate to some deep learning methods, which unsupervised characteristics show it has potential for applications on rail transit trains.

关键词： Tensors Fault diagnosis Clustering algorithms signal processing algorithms Monitoring Rails Time complexity Bogie-bearing tensor clustering variable working conditions intelligent fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Diffusion Bayesian Decorrelation algorithms Over Networks

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 571-586页

作者： Huang, Fuyi Zhang, Sheng Zhang, Jiashu Chen, Hongyang Sayed, Ali H. Guangxi Univ Sch Comp Elect & Informat Guangxi Key Lab Multimedia Commun & Network Techno Nanning 530004 Peoples R China Southwest Jiaotong Univ Sch Informat Sci & Technol Chengdu 611756 Peoples R China Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 611756 Peoples R China Res Ctr Graph Comp Zhejiang Lab Hangzhou 311121 Peoples R China Ecole Polytech Federalede Lausanne Sch Engn CH-1015 Lausanne Switzerland

The convergence rate of the diffusion normalized least mean squares (NLMS) algorithm can be speeded up by decorrelation of signals. However, the diffusion decorrelation NLMS algorithm confronts the conflicting requirements of fast convergence rate and small steady-state error. To address the issue, this paper proposes a family of diffusion Bayesian decorrelation least mean squares (DBDLMS) algorithms based on decorrelated observation models. Firstly, the weight update equations of the proposed DBDLMS algorithms are obtained by performing Bayesian inference over the decorrelated observation models, with variable step-sizes emerging naturally to help address the conflicting requirement. Secondly, the update equations of the decorrelation coefficient vectors are inferred from the Bayesian perspective, with the variable step-sizes emerging again. Subsequently, the performance analysis of the proposed DBDLMS algorithms is carried out. Moreover, a simple and effective approach is derived to estimate the free parameters for the proposed DBDLMS algorithms. Finally, the learning performance of the proposed algorithms are verified by Monte Carlo simulations.

关键词： Decorrelation signal processing algorithms Bayes methods Estimation Convergence Inference algorithms Steady-state Adaptive networks decorrelation diffusion strategy distributed processing least mean squares

来源：评论

学校读者我要写书评

暂无评论

Fast MSE-Based Sampling of Bandlimited Graph signals via Low-Pass Impulse Responses

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 4207-4223页

作者： Wang, Fen Cheung, Gene Ye, Minxiang Li, Taihao Feng, Yi-Tian Zhejiang Lab Hangzhou 311121 Peoples R China York Univ Dept EECS Toronto ON M3J 1P3 Canada

Sampling is a fundamental problem in graph signal processing that selects a node subset to collect samples, so that data in the remaining nodes can be well recovered. Existing eigen-decomposition-free (ED-free) graph sampling schemes are not designed to minimize mean square error (MMSE) of reconstructed bandlimited graph signals, often resulting in sub-par MSE performance. In this paper, we propose a lightweight ED-free algorithm to minimize an approximate MSE objective using per-node impulse responses of an ideal low-pass graph filter. Specifically, we first derive a proxy of the MMSE greedy sampling objective without matrix inverse. We then define node-dependent impulse responses of an ideal low-pass graph filter-analogous to the sinc function in traditional signal processing-which can be approximated very fast without ED. We use these response vectors to reformulate our derived sampling objective, then show that the optimal sampling set has supported low-pass impulse responses that are as orthogonal as possible-defaulting to uniform sampling for 1D regular kernels when the graph Fourier basis is DFT. For optimization, we propose a fast sampling algorithm to evaluate candidates via vector-vector multiplications by reusing previous greedy results. For faster sampling, we relax the MMSE-based greedy objective to a bounded approximation, so that candidate nodes can be easily appraised using simple scalar multiplications. Extensive experiments show that our sampling method achieved state-of-the-art sampling speed and had the best MSE performance among deterministic ED-free sampling methods in various scenarios.

关键词： Laplace equations Complexity theory signal processing algorithms Sampling methods Matrix decomposition Eigenvalues and eigenfunctions Approximation algorithms Graph sampling graph signal processing optimality design eigen-decomposition

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：