The proceedings contain 86 papers. The topics discussed include: sparse array and precoding design for integrated sensing and communications systems;geometry-aided near-field MIMO communications via forward-backward b...
ISBN:
(纸本)9798350344813
The proceedings contain 86 papers. The topics discussed include: sparse array and precoding design for integrated sensing and communications systems;geometry-aided near-field MIMO communications via forward-backward beamformer training;a decentralized asynchronous optimization algorithm with an application to phase retrieval;DynaPA: dynamic power allocation for improved exploration-exploitation in active sensing;receiver antenna allocation for joint sensing and communications;labeling sequential data from noisy annotations;calibration of polarimetric antenna arrays using neural networks;variable selection for Max-Affine regression via sparse gradient descent;experimental evaluation of a null-steered performance weighted blended beamformer;and distributed sparse subspace clustering by k-means subspace fusion.
The proceedings contain 146 papers. The topics discussed include: unified asymptotic distribution of subspace projectors in complex elliptically symmetric models;semantic labeling for point cloud detection and registr...
ISBN:
(纸本)9781665452458
The proceedings contain 146 papers. The topics discussed include: unified asymptotic distribution of subspace projectors in complex elliptically symmetric models;semantic labeling for point cloud detection and registration using the universal manifold embedding: statistical analysis;a simple and tight Bayesian lower bound for direction-of-arrival estimation;comparing iterative and least-squares based phase noise tracking in receivers with 1-bit quantization and oversampling;detection in human-sensor systems under quantum prospect theory using Bayesian persuasion frameworks;prediction of shock formation from boundary measurements;efficient sparse reduced-rank regression with covariance estimation;and a strictly bounded deep network for unpaired cyclic translation of medical images.
The proceedings contain 94 papers. The topics discussed include: federated channel learning for intelligent reflecting surfaces with fewer pilot signals;statistical analyses of measured forward-looking sonar echo data...
ISBN:
(纸本)9781665406338
The proceedings contain 94 papers. The topics discussed include: federated channel learning for intelligent reflecting surfaces with fewer pilot signals;statistical analyses of measured forward-looking sonar echo data in a shallow water environment;passive angle-doppler profile estimation for narrowband digitally modulated wireless signals;dynamic TDD enabled distributed antenna array massive MIMO system;joint source enumeration and direction finding without eigendecomposition for satellite navigation receiver;sparse signal recovery using a binary program;gradient-descent adaptive filtering using gradient adaptive step-size;non-coherent source localization with distributed sensor array networks;and joint location and channel error optimization for beamforming design for multi-RIS assisted MIMO system.
In big data analytics, the collected data may be contaminated by heavy-tailed noises or outliers, and the sample size may be insufficient. In this paper, we study robust sparse regression under the presence of asymmet...
详细信息
ISBN:
(纸本)9798350344820;9798350344813
In big data analytics, the collected data may be contaminated by heavy-tailed noises or outliers, and the sample size may be insufficient. In this paper, we study robust sparse regression under the presence of asymmetric heavy-tailed errors within a high-dimensional setting, where the ambient dimension can exceed the sample size. The estimation problem is formulated as an l(1) constrained regression with Huber loss function. We propose a simple projected gradient descent algorithm to solve the problem and establish its convergence properties, accounting for both computational and statistical errors. Under mild conditions, we demonstrate that the successive iterates converge at a linear rate to an estimate within the statistical precision of the model. Numerical experiments validate the robust estimation performance of the proposed method across various heavy-tail distribution settings.
This paper addresses the problem of two-way sparse reduced-rank regression (TSRRR), which aims to estimate a coefficient matrix that is both low-rank and two-way sparse (sparse in both rows and columns) within a multi...
详细信息
ISBN:
(数字)9798350344813
ISBN:
(纸本)9798350344820;9798350344813
This paper addresses the problem of two-way sparse reduced-rank regression (TSRRR), which aims to estimate a coefficient matrix that is both low-rank and two-way sparse (sparse in both rows and columns) within a multiple response linear regression model. We formulate TSRRR as a nonconvex optimization problem and propose an efficient, scalable iterative algorithm called Scaled Gradient Descent with Hard Thresholding (ScaledGDT) to solve it. We demonstrate that the iterates obtained by ScaledGDT converge linearly to a region within the statistical error of the ground truth, and this convergence rate is independent of the condition number of the coefficient matrix. Furthermore, we prove that the statistical error rate achieved by ScaledGDT is nearly minimax optimal. Experimental results confirm our theoretical findings and showcase the competitive performance of ScaledGDT.
Channel estimation is always implemented in communication systems to overcome the effect of interference and noise. Especially, in wireless communications, this task is more challenging to improve system performance w...
详细信息
ISBN:
(纸本)9781665452458
Channel estimation is always implemented in communication systems to overcome the effect of interference and noise. Especially, in wireless communications, this task is more challenging to improve system performance while saving resources. This paper focuses on investigating the impact of geometries of antenna arrays on the performance of structured channel estimation in massive MIMO-OFDM systems. We use Cram ' er Rao Bound to analyze errors in two methods, i.e., training-based and semi-blind-based channel estimations. The simulation results show that the latter gets significantly better performance than the former. Besides, the system with Uniform Cylindrical array outperforms the traditional Uniform Linear array one in both estimation methods.
The term fractal refers to the fractional dimensions that have recursive nature and when clubbed with the properties of sparse arrays leads to the generation of a novel array called a sparse fractal array. In this pap...
详细信息
ISBN:
(纸本)9781665452458
The term fractal refers to the fractional dimensions that have recursive nature and when clubbed with the properties of sparse arrays leads to the generation of a novel array called a sparse fractal array. In this paper, we extend our research to the 2D domain by introducing planar sparse arrays which generate hole-free difference coarray and have O(N-2) elements just like the OBA but here in the new closed box form, with the additional property of fractal arrays along with sparseness. To estimate azimuth and elevation angle we have designed planar sparse fractal arrays using nested arrays and coprime arrays as the fundamental basic generating array which helps in achieving a high degree of freedom which makes it useful for DOA estimation. Simulations show that the proposed planar arrays have the better estimation performance when compared with existing planar arrays like URA, OBA, and CPA.
Multichannel acoustic signalprocessing is a well-established and powerful tool to exploit the spatial diversity between a target signal and nontarget or noise sources for signal enhancement. However, the textbook sol...
详细信息
Multichannel acoustic signalprocessing is a well-established and powerful tool to exploit the spatial diversity between a target signal and nontarget or noise sources for signal enhancement. However, the textbook solutions for optimal data-dependent spatial filtering rest on the knowledge of second-order statistical moments of the signals, which have traditionally been difficult to acquire. In this contribution, we compare model-based, purely data-driven, and hybrid approaches to parameter estimation and filtering, where the latter tries to combine the benefits of model-based signalprocessing and data-driven deep learning to overcome their individual deficiencies. We illustrate the underlying design principles with examples from noise reduction, source separation, and dereverberation.
Tracking signals in dynamic environments presents difficulties in both analysis and implementation. In this work, we expand on a class of subspace tracking algorithms which utilize the Grassmann manifold - the set of ...
详细信息
ISBN:
(纸本)9798350344820;9798350344813
Tracking signals in dynamic environments presents difficulties in both analysis and implementation. In this work, we expand on a class of subspace tracking algorithms which utilize the Grassmann manifold - the set of linear subspaces of a high-dimensional vector space. We design regularized least squares algorithms based on common manifold operations and intuitive dynamical models. We demonstrate the efficacy of the approach for a narrowband beamforming scenario, where the dynamics of multiple signals of interest are captured by motion on the Grassmannian.
Direction augmentation (DA), followed by a subspace method such as MUSIC or ESPRIT, is a successful approach that enables localization of more uncorrelated sources than sensors with a proper sparse linear array. In th...
详细信息
ISBN:
(纸本)9781665452458
Direction augmentation (DA), followed by a subspace method such as MUSIC or ESPRIT, is a successful approach that enables localization of more uncorrelated sources than sensors with a proper sparse linear array. In this paper, we carry out a nonasymptotic performance analysis of DA-ESPRIT in the practical scenario with finitely many snapshots. We show that more uncorrelated sources than sensors are guaranteed, with overwhelming probability, to be localized using DA-ESPRIT if the number of snapshots is greater than an explicit, problem-dependent threshold. Our result does not require a fixed source separation condition, which makes it unique among existing results. Numerical results corroborating our analysis are provided.
暂无评论