Search

While many distributed optimization algorithms have been proposed for solving smooth or convex problems over the networks, few of them can handle non-convex and non-smooth problems. Based on a proximal primal-dual approach, this paper presents a new (stochastic) distributed algorithm with Nesterov momentum for accelerated optimization of non-convex and non-smooth problems. Theoretically, we show that the proposed algorithm can achieve an $\epsilon$ -stationary solution under a constant step size with $\mathcal {O}(1/\epsilon ^2)$ computation complexity and $\mathcal {O}(1/\epsilon)$ communication complexity when the epigraph of the non-smooth term is a polyhedral set. When compared to the existing gradient tracking based methods, the proposed algorithm has the same order of computation complexity but lower order of communication complexity. To the best of our knowledge, the presented result is the first stochastic algorithm with the $\mathcal {O}(1/\epsilon)$ communication complexity for non-convex and non-smooth problems. Numerical experiments for a distributed non-convex regression problem and a deep neural network based classification problem are presented to illustrate the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we extend the bilinear generalized approximate message passing (BiG-AMP) approach, originally proposed for high-dimensional generalized bilinear regression, to the multi-layer case for the handling of cascaded problem such as matrix-factorization problem arising in relay communication among others. Assuming statistically independent matrix entries with known priors, the new algorithm called ML-BiGAMP could approximate the general sum-product loopy belief propagation (LBP) in the high-dimensional limit enjoying a substantial reduction in computational complexity. We demonstrate that, in large system limit, the asymptotic MSE performance of ML-BiGAMP could be fully characterized via a set of simple one-dimensional equations termed state evolution (SE). We establish that the asymptotic MSE predicted by ML-BiGAMP’ SE matches perfectly the exact MMSE predicted by the replica method, which is well-known to be Bayes-optimal but infeasible in practice. This consistency indicates that the ML-BiGAMP may still retain the same Bayes-optimal performance as the MMSE estimator in high-dimensional applications, although ML-BiGAMP's computational burden is far lower. As an illustrative example of the general ML-BiGAMP, we provide a detector design that could estimate the channel fading and the data symbols jointly with high precision for the two-hop amplify-and-forward relay communication systems. [ABSTRACT FROM AUTHOR]

This paper proposes an efficient algorithm for robust sensor placement with the purpose of recovering a source signal from noisy measurements. To model uncertainty on the spatially-variant sensors gain and on the spatially correlated noise, we assume that both are realizations of Gaussian processes. Since the signal to noise ratio (SNR) is also uncertain in this context, to achieve a robust signal extraction, we propose a new placement criterion based on the maximization of the probability that the SNR exceeds a given threshold. This criterion can be easily evaluated using the Gaussian process assumption. Moreover, to reduce the computational complexity of the joint maximization of the criterion with respect to all sensor positions, we suggest a sequential maximization approach, where the sensor positions are chosen one at a time. Finally, we present numerical results showing the superior robustness of the proposed approach when compared to standard sensor placement criteria aimed at interpolating the spatial gain and to a recently proposed criterion aimed at maximizing the average SNR. [ABSTRACT FROM AUTHOR]

The first moment and second central moments of the portfolio return, a.k.a. mean and variance, have been widely employed to assess the expected profit and risk of the portfolio. Investors pursue higher mean and lower variance when designing the portfolios. The two moments can well describe the distribution of the portfolio return when it follows the Gaussian distribution. However, the real world distribution of assets return is usually asymmetric and heavy-tailed, which is far from being a Gaussian distribution. The asymmetry and the heavy-tailedness are characterized by the third and fourth central moments, i.e., skewness and kurtosis, respectively. Higher skewness and lower kurtosis are preferred to reduce the probability of extreme losses. However, incorporating high-order moments in the portfolio design is very difficult due to their non-convexity and rapidly increasing computational cost with the dimension. In this paper, we propose a very efficient and convergence-provable algorithm framework based on the successive convex approximation (SCA) algorithm to solve high-order portfolios. The efficiency of the proposed algorithm framework is demonstrated by the numerical experiments. [ABSTRACT FROM AUTHOR]

In this paper we consider maximum-likelihood (ML) MIMO detection under one-bit quantized observations and binary symbol constellations. This problem is motivated by the recent interest in adopting coarse quantization in massive MIMO systems—as an effective way to scale down the hardware complexity and energy consumption. Classical MIMO detection techniques consider unquantized observations, and many of them are not applicable to the one-bit MIMO case. We develop a new non-convex optimization algorithm for the one-bit ML MIMO detection problem, using a strategy called homotopy optimization. The idea is to transform the ML problem into a sequence of approximate problems, from easy (convex) to hard (close to ML), and with each problem being a gradual modification of its previous. Then, our attempt is to iteratively trace the solution path of these approximate problems. This homotopy algorithm is well suited to the application of deep unfolding, a recently popular approach for turning certain model-based algorithms into data-driven, and performance enhanced, ones. While our initial focus is on one-bit MIMO detection, the proposed technique also applies naturally to the classical unquantized MIMO detection. We performed extensive simulations and show that the proposed homotopy algorithms, both non-deep and deep, have satisfactory bit-error probability performance compared to many state-of-the-art algorithms. Also, the deep homotopy algorithm has attractively low computational complexity. [ABSTRACT FROM AUTHOR]

The Probability Hypothesis Density (PHD) and Cardinalized PHD (CPHD) filters are popular solutions to the multitarget tracking problem due to their low complexity and ability to estimate the number and states of targets in cluttered environments. The PHD filter propagates the first-order moment (i.e. mean) of the number of targets while the CPHD propagates the cardinality distribution in the number of targets, albeit for a greater computational cost. Introducing the Panjer point process, this paper proposes a Second-Order PHD (SO-PHD) filter, propagating the second-order moment (i.e., variance) of the number of targets alongside its mean. The resulting algorithm is more versatile in the modeling choices than the PHD filter, and its computational cost is significantly lower compared to the CPHD filter. This paper compares the three filters in statistical simulations which demonstrate that the proposed filter reacts more quickly to changes in the number of targets, i.e., target births and target deaths, than the CPHD filter. In addition, a new statistic for multiobject filters is introduced in order to study the correlation between the estimated number of targets in different regions of the state space, and propose a quantitative analysis of the spooky effect for the three filters. [ABSTRACT FROM PUBLISHER]

Grant-free random access is a promising protocol to support massive access in beyond fifth-generation (B5G) cellular Internet-of-Things (IoT) with sporadic traffic. Specifically, in each coherence interval, the base station (BS) performs joint activity detection and channel estimation (JADCE) before data transmission. Due to the deployment of a large-scale antennas array and the existence of a huge number of IoT devices, JADCE usually has high computational complexity and needs long pilot sequences. To solve these challenges, this paper proposes a dimension reduction method, which projects the original device state matrix to a low-dimensional space by exploiting its sparse and low-rank structure. Then, we develop an optimized design framework with a coupled full column rank constraint for JADCE to reduce the size of the search space. However, the resulting problem is non-convex and highly intractable, for which the conventional convex relaxation approaches are inapplicable. To this end, we propose a logarithmic smoothing method for the non-smoothed objective function and transform the interested matrix to a positive semidefinite matrix, followed by giving a Riemannian trust-region algorithm to solve the problem in complex field. Simulation results show that the proposed algorithm is efficient to a large-scale JADCE problem and requires shorter pilot sequences than the state-of-art algorithms which only exploit the sparsity of device state matrix. [ABSTRACT FROM AUTHOR]

In recent years, the sources localization has noticed an increase in research conducted on the problem of mixed far-field sources (FFSs) and near-field sources (NFSs). The main assumption of the existing researches is that the signals should be uncorrelated. Therefore, they cannot be used for multipath environments. The present paper provides a method called components separation algorithm (CSA) for the localization of multiple mixed FFSs and NFSs, including uncorrelated, lowly correlated and coherent signals. Firstly, by constructing one special cumulant matrix, and using a MUSIC-based technique, the noncoherent DOA vector (NDOAV) is extracted. By constructing another special cumulant matrix, and with respect to NDOAV, an estimate of the range, as well as a signal classification is obtained for noncoherent sources. Then, by estimating their kurtosis, the noncoherent component and consequently the coherent one of the second cumulant matrix is obtained. Finally, by introducing a novel approach based on squaring, projection, spatial smoothing, array interpolation transform and coherent component restoring, the parameters of coherent signals in each coherent group are estimated separately. The CSA prevents severe loss of the aperture. Furthermore, it does not require any pairing. The simulation results validate its satisfactory performance in terms of estimation accuracy, resolution, computational complexity, reasonable classification, and also its robustness against lowly correlated sources. [ABSTRACT FROM AUTHOR]

In this paper, we develop a kernel adaptive filter for quaternion data, using stochastic information gradient (SIG) cost function based on the information theoretic learning (ITL) approach. The new algorithm (QKSIG) is useful for quaternion-based kernel applications of nonlinear filtering. Adaptive filtering in quaterion domain intrinsically incorporates component-wise real valued cross-correlation or the coupling within the dimensions of the quaternion input. We apply generalized Hamilton-real (GHR) calculus that is applicable to quaternion Hilbert space for evaluating the cost function gradient. The QKSIG algorithm minimizes Shannon's entropy of the error between the filter output and desired response and minimizes the divergence between the joint densities of input-desired and input-output pairs. The SIG technique reduces the computational complexity of the error entropy estimation. Here, ITL with SIG approach is applied to quaternion adaptive filtering for three different reasons. First, it reduces the algorithm computational complexity compared to our previous work quaternion kernel minimum error entropy algorithm (QKMEE). Second, it improves the filtering performance by considering the coupling within the dimensions of the quaternion input. Third, it performs better in biased or non-Gaussian signal and noise environments due to ITL approach. We present convergence analysis and steady-state performance analysis results of the new algorithm (QKSIG). Simulation results are used to show the behavior of the new algorithm QKSIG in quaternion non-Gaussian signal and noise environments compared to the existing ones such as quadruple real-valued kernel stochastic information gradient (KSIG) and quaternion kernel LMS (QKLMS) algorithms. [ABSTRACT FROM AUTHOR]

In this paper, a computationally efficient algorithm for Bayesian joint change point detection (CPD) in multiple time series is presented. The data generation model includes a number of change configurations (CC), each affecting a unique subset of the time series, which introduces correlation between the positions of change points (CPs) in the monitored time series. The inference objective is to identify joint changes and the associated CC. The algorithm consists of two stages: First, a univariate CPD algorithm is applied separately to each of the involved time series. The outcomes of this step are maximum a posteriori (MAP) detected CPs and posterior distributions of CPs conditioned on the MAP CPs. These outcomes are used in combination to approximate the posterior for the CCs. In the second algorithm stage, dynamic programming is used to find the maxima of this approximate CC posterior. The algorithm is applied to synthetic data, and it is shown to be both significantly faster and more accurate compared to a previously proposed algorithm designed to solve similar problems. Also, the initial algorithm is extended with steps from the maximization–maximization algorithm, which allows the hyperparameters of the data generation model to be estimated jointly with the CCs, and we show that these estimates coincide with estimates obtained from a Markov chain Monte Carlo algorithm. [ABSTRACT FROM AUTHOR]

This paper considers the reconstruction of a discrete-valued random vector from possibly underdetermined linear measurements using sum-of-absolute-value (SOAV) optimization. The proposed algorithm, referred to as discreteness-aware approximate message passing (DAMP), is based on the idea of approximate message passing (AMP), which has been originally proposed for compressed sensing. The DAMP algorithm has low computational complexity and its performance in the large system limit can be predicted analytically via state evolution framework, where we provide a condition for the exact reconstruction with DAMP in the noise-free case. From the analysis, we also propose a method to determine the parameters of the SOAV optimization. Moreover, based on the state evolution, we provide Bayes optimal DAMP, which has the minimum mean-square-error at each iteration of the algorithm. Simulation results show that the DAMP algorithms can reconstruct the discrete-valued vector from underdetermined linear measurements and the empirical performance agrees with our theoretical results in large-scale systems. When the problem size is not large enough, the SOAV optimization with the proposed parameters can achieve better performance than the DAMP algorithms for high signal-to-noise ratio. [ABSTRACT FROM AUTHOR]

Classification with a sparsity constraint on the solution plays a central role in many high dimensional signal processing applications. In some cases, the features can be grouped together, so that entire subsets of features can be selected or discarded. In many applications, however, this can be too restrictive. In this paper, we are interested in a less restrictive form of structured sparse feature selection: We assume that while features can be grouped according to some notion of similarity, not all features in a group need be selected for the task at hand. The Sparse Group Lasso (SGL) was proposed to solve problems of this form. The main contributions of this paper are a new procedure called Sparse Overlapping Group (SOG) lasso, an extension to the SGL to overlapping groups and theoretical sample complexity bounds for the same. We establish model selection error bounds that specializes to many other cases. We experimentally validate our proposed method on both real and toy datasets. [ABSTRACT FROM AUTHOR]

BigBand is a technique for wideband spectrum sensing (WSS) that can capture gigahertz of sparse spectrum in real time by using shifted multiple channels without sampling the signal at GS/s. In this paper, we focus on enforcing BigBand with the proposed improved algorithm, namely, AD-BigBand, for efficient and robust computation. AD-BigBand converts the nonlinear process (locating frequency and computing the spectrum value) of sparse WSS into two steps of solving linear equations. In particular, we define an r -degree frequency locator polynomial to rapidly locate nonzero frequencies. The computing complexity of the proposed method decreases from O(K{\log ^2}K ({{{n\log K} \over K}})^{\log K}) of shifted sampling based BigBand to O(K{\log ^2}K)$, where the $K$-sparse signals of bandwitdth $n$ are subsampled with arithmetic time-shifted sensing channels. We implement AD-BigBand on a commercial four-channel acquisition card. Experimental results show that AD-BigBand improves the WSS capabilities and exhibits higher processing speed and lower error spectrum construction rate than BigBand, especially in the case of relative low signal-to-noise ratio. [ABSTRACT FROM AUTHOR]

Conventional direction-of-arrival (DOA) estimation methods are sensitive to outlier measurements. Therefore, their performance may degrade substantially in the presence of impulsive noise. In this paper, we address the problem of DOA estimation in additive outliers from the perspective of sparse Bayesian learning (SBL). A Bayes-optimal algorithm is devised for robust DOA estimation, which can achieve excellent performance in terms of resolution and accuracy. To reduce the computational complexity of the SBL scheme, a fast alternating algorithm is also developed. New grid-refining procedures are further introduced into these two proposed algorithms to efficiently fix the off-grid gap. As our solutions do not require the prior knowledge of the number of sources and can resolve highly correlated or coherent sources, it is expected that they have higher applicability. Simulation results verify the outlier-robust performance of the SBL approach. [ABSTRACT FROM AUTHOR]

This paper develops a novel algorithm, termed SPARse Truncated Amplitude flow (SPARTA), to reconstruct a sparse signal from a small number of magnitude-only measurements. It deals with what is also known as sparse phase retrieval (PR), which is NP-hard in general and emerges in many science and engineering applications. Upon formulating sparse PR as an amplitude-based nonconvex optimization task, SPARTA works iteratively in two stages: In stage one, the support of the underlying sparse signal is recovered using an analytically well-justified rule, and subsequently a sparse orthogonality-promoting initialization is obtained via power iterations restricted on the support; and in the second stage, the initialization is successively refined by means of hard thresholding based gradient-type iterations. SPARTA is a simple yet effective, scalable, and fast sparse PR solver. On the theoretical side, for any n-dimensional k-sparse (k ≪ n) signal x with minimum (in modulus) nonzero entries on the order of (1/√k)||x||2, SPARTA recovers the signal exactly (up to a global unimodular constant) from about k2 log n random Gaussian measurements with high probability. Furthermore, SPARTA incurs computational complexity on the order of k2 n log n with total runtime proportional to the time required to read the data, which improves upon the state of the art by at least a factor of k. Finally, SPARTA is robust against additive noise of bounded support. Extensive numerical tests corroborate markedly improved recovery performance and speedups of SPARTA relative to existing alternatives. [ABSTRACT FROM AUTHOR]

This paper examines the mean-square error performance of diffusion stochastic algorithms under a generalized coordinate-descent scheme. In this setting, the adaptation step by each agent is limited to a random subset of the coordinates of its stochastic gradient vector. The selection of coordinates varies randomly from iteration to iteration and from agent to agent across the network. Such schemes are useful in reducing computational complexity at each iteration in power-intensive large data applications. They are also useful in modeling situations where some partial gradient information may be missing at random. Interestingly, the results show that the steady-state performance of the learning strategy is not always degraded, while the convergence rate suffers some degradation. The results provide yet another indication of the resilience and robustness of adaptive distributed strategies. [ABSTRACT FROM AUTHOR]

In multiple-input multiple-output radar, to localize a target and estimate its reflection coefficient, a given cost function is usually optimized over a grid of points. The performance of such algorithms is directly affected by the grid resolution. Increasing the number of grid points enhances the resolution of the estimator but also increases its computational complexity exponentially. In this paper, two reduced complexity algorithms are derived based on Capon and amplitude and phase estimation (APES) to estimate the reflection coefficient, angular location, and Doppler shift of multiple moving targets. By exploiting the structure of the terms, the cost function is brought into a form that allows us to apply the two-dimensional fast Fourier transform (2D-FFT) and reduce the computational complexity of estimation. Using low resolution 2D-FFT, the proposed algorithm identifies suboptimal estimates and feeds them as initial points to the derived Newton gradient algorithm. In contrast to the grid-based search algorithms, the proposed algorithm can optimally estimate on- and off-the-grid targets in very low computational complexity. A new APES cost function with better estimation performance is also discussed. Generalized expressions of the Cramér–Rao lower bound are derived to assess the performance of the proposed algorithm. [ABSTRACT FROM PUBLISHER]

Based on the minimum noise subspace (MNS) method previously introduced in the context of blind channel identification, generalized minimum noise subspace (GMNS) is proposed in this paper for array processing that generalizes MNS with respect to the availability of only a fixed number of parallel computing units. Different batch and adaptive algorithms are then introduced for fast and parallel computation of signal (principal) and noise (minor) subspaces. The computational complexity of GMNS and its related estimation accuracy are investigated by simulated experiments and a real-life experiment in radio astronomy. It is shown that GMNS represents an excellent tradeoff between the computational gain and the subspace estimation accuracy, as compared to several standard subspace methods. [ABSTRACT FROM PUBLISHER]

Particle filters are broadly used to approximate posterior distributions of hidden states in state-space models by means of sets of weighted particles. While the convergence of the filter is guaranteed when the number of particles tends to infinity, the quality of the approximation is usually unknown but strongly dependent on the number of particles. In this paper, we propose a novel method for assessing the convergence of particle filters in an online manner, as well as a simple scheme for the online adaptation of the number of particles based on the convergence assessment. The method is based on a sequential comparison between the actual observations and their predictive probability distributions approximated by the filter. We provide a rigorous theoretical analysis of the proposed methodology and, as an example of its practical use, we present simulations of a simple algorithm for the dynamic and online adaptation of the number of particles during the operation of a particle filter on a stochastic version of the Lorenz 63 system. [ABSTRACT FROM PUBLISHER]

The block diagonalization (BD) scheme is a low-complexity suboptimal precoding technique for multiuser multiple input-multiple output (MIMO) downlink channels, which completely precancels the multiuser interference. Accordingly, the precoder of each user lies in the null space of other users' channel matrices. In this paper, we propose an iterative algorithm using QR decompositions (QRDs) to compute the precoders. Specifically, to avoid dealing with a large concatenated matrix, we apply the QRD to a sequence of matrices of lower dimensions. One problem of BD schemes is that the number of users that can be simultaneously supported is limited due to zero interference constraints. When the number of users is large, a set of users must be selected, and selection algorithms should be designed to exploit the multiuser diversity gain. Finding the optimal set of users requires an exhaustive search, which has too high computational complexity to be practically useful. Based on the iterative precoder design, this paper proposes a low-complexity user selection algorithm using a greedy method, in which the precoders of selected users are recursively updated after each selection step. The selection metric of the proposed scheduling algorithm relies on the product of the squared row norms of the effective channel matrices, which is related to the eigenvalues by the Hadamard and Schur inequalities. An asymptotic analysis is provided to show that the proposed algorithm can achieve the optimal sum rate scaling of the MIMO broadcast channel. The numerical results show that the proposed algorithm achieves a good trade-off between sum rate performance and computational complexity. When users suffer different channel conditions, providing fairness among users is of critical importance. To address this problem, we also propose two fair scheduling (FS) algorithms, one imposing fairness in the approximation of the data rate, and another directly imposing fairness in the product of the squared row norms of the effective channel matrices. [ABSTRACT FROM PUBLISHER]

In this paper, we consider a Partial Interference Alignment and Interference Detection (PIAID) design for K-user quasi-static MIMO interference channels with discrete constellation inputs. Each transmitter has M antennas and transmits L independent data streams to the desired receiver with N receive antennas. We focus on the case where not all K-1 interfering transmitters can be aligned at every receiver. As a result, there will be residual interference at each receiver that cannot be aligned. Each receiver detects and cancels the residual interference based on the constellation map. However, there is a window of unfavorable interference profile at the receiver for Interference Detection (ID). In this paper, we propose a low complexity Partial Interference Alignment scheme in which we dynamically select the user set for IA so as to create a favorable interference profile for ID at each receiver. We first derive the average symbol error rate (SER) by taking into account of the non-Guassian residual interference due to discrete constellation. Using graph theory, we then devise a low complexity user set selection algorithm for the PIAID scheme, which minimizes the asymptotically tight bound for the average end-to-end SER performance. Moreover, we substantially simplify interference detection at the receiver using Semi-Definite Relaxation (SDR) techniques. It is shown that the SER performance of the proposed PIAID scheme has significant gain compared with various conventional baseline solutions. [ABSTRACT FROM PUBLISHER]

This paper proposes a low complexity n-dimensional (nD) FastICA algorithm and architecture by introducing the concept of coordinate rotation where n\geq 2. The proposed algorithm can merge the two key steps of conventional FastICA—preprocessing and update and is therefore capable of reducing the hardware complexity of the conventional FastICA significantly as demonstrated in this paper. Hardware implementation can further be simplified due to the recursive nature of the proposed algorithm where the same 2D hardware module can be used as the fundamental core to implement nD architecture. Together with the algorithm formulation, its functionality is also validated and hardware complexity is analyzed and compared with the conventional nD FastICA. [ABSTRACT FROM PUBLISHER]

Achieving the boundary of the capacity region in the multiple-input multiple-output (MIMO) broadcast channel requires the use of dirty paper coding (DPC). As practical nearly optimum implementations of DPC are computationally complex, purely linear approaches are often used instead. However, in this case, the problem of maximizing a weighted sum rate constitutes a nonconvex and, in most cases, also a combinatorial optimization problem. In this paper, we present two heuristic nearly optimum algorithms with reduced computational complexity. For this purpose, a lower bound for the weighted sum rate under linear zero-forcing constraints is used. Based on this bound, both greedy algorithms successively allocate data streams to users. In each step, the user is determined that is given an additional data stream such that the increase in weighted sum rate becomes maximum. Thereby, the data stream allocations and filters obtained in the previous steps are kept fixed and only the filter corresponding to the additional data stream is optimized. The first algorithm determines the receive and transmit filters directly in the downlink. The other algorithm operates in the dual uplink, from which the downlink transmit and receive filters can be obtained via the general rate duality leading to nonzero-forcing in the downlink. Simulation results reveal marginal performance losses compared to more complex algorithms. [ABSTRACT FROM AUTHOR]

This paper introduces Bayes risk (expected loss) as a criterion for linear equalization. Since the probability of error is equal to the Bayes risk (BR) for a particular binary loss function, this work is a natural generalization of previous works on minimum probability of error (PE) equalizers. Adaptive equalization algorithms are developed that minimize the BR. Like the minimum PE equalizers, the BR algorithms have low computational complexity which is comparable to that of the LMS algorithm. The advantage of the BR criterion is that the loss function can be specified in a manner that accelerates adaptive equalizer convergence relative to the minimum PE adaptive algorithm as illustrated in simulation examples. Besides introducing a new criterion, this paper provides another independent contribution to the field of PE minimizing equalization. While most prior works focus on M-ary QAM type modulations with rectangular decision regions, this paper uses upper bounds on the probabilities of certain events to yield tractable mathematics that apply to two-dimensional constellations with arbitrarily shaped decision regions. The resulting adaptive algorithm use the full information available in the phase of the error signal, whereas previous algorithms use a quantized version of this error phase. [ABSTRACT FROM AUTHOR]

Very often, random signals are modeled as autoregressive moving-average (ARMA) processes in engineering and scientific applications. The acquisition of the second-order statistics or the calculation of the autocorrelation function for an ARMA process is very important in those applications. In this paper, we discuss two kinds of ARMA-autocorrelation computation approaches, namely the recursive approach and the direct approach. To overcome the problems of memory usage and computational burden, we design a new ARMA-autocorrelation calculation algorithm which belongs to the direct approach. Our novel algorithm originates from the partial fractional decomposition for the rational trigonometric functions and the associated definite integrals. For comparison, we also provide the theoretical analysis of computational complexity for our new scheme and the conventional recursion-based algorithm. From our studies, it can be shown that our new ARMA-autocorrelation calculation method is more efficient than the conventional algorithm when the underlying autocorrelation function is long or the corresponding power spectrum possesses the narrowband characteristics. On the other hand, the conventional algorithm is more efficient than our new algorithm when the model orders of the ARMA process are large' and the underlying autocorrelation function is short (the corresponding power spectrum is wideband). Since our proposed new scheme involves the root-finding of a polynomial, the effect, of the error-tolerance in solving polynomials on the induced complexity is also discussed in this paper. [ABSTRACT FROM AUTHOR]

The paper presents two formulations of causal cubic splines with equidistant knots. Both are based on a causal direct B-spline filter with parallel or cascade implementation. In either implementation, the causal part of the impulse response is realized with an efficient infinite-impulse-response (HR) structure, while only the anticausal part is approximated with a finite-order finite-impulse-response (FIR) filter. Resulting cubic coefficients are computed from the causal B-spline coefficients by using a third-order output FIR filter with either single-input multiple-output (SIMO) or multiple-input multiple-output (MIMO) structure, depending on the chosen formulation of the cubic spline. The paper demonstrates and proves that the properties of the resulting causal splines are quite different, whether they are based on a more popular B-spline formulation, or a bit neglected tridiagonal matrix formulation. It is shown that the proposed low-complexity but accurate causal interpolators can be realized for many practical applications with the delay of only a few samples. [ABSTRACT FROM AUTHOR]

The kurtosis maximization criterion has been effectively used for blind spatial extraction of one source from an instantaneous mixture of multiple non-Gaussian sources, such as the kurtosis maximization algorithm by Ding and Nguyen, and the fast kurtosis maximization algorithm (FKMA) by Chi and Chen. By empirical studies, we found that the smaller the normalized kurtosis magnitude of the extracted source signal, the worse the performance of these algorithms. In this paper, with the assumption that each source is a non-Gaussian linear process, a novel blind source extraction algorithm, called turbo source extraction algorithm (TSEA), is proposed. The ideas of the TSEA are to exploit signal temporal properties for increasing the normalized kurtosis magnitude, and to apply spatial and temporal processing in a cyclic fashion to improve the signal extraction performance. The proposed TSEA not only outperforms the FKMA, but also shares the convergence and computation advantages enjoyed by the latter. This paper also considers the extraction of multiple sources, also known as source separation, by incorporating the proposed TSEA into the widely used multistage successive cancellation (MSC) procedure. A problem with the MSC procedure is its susceptibility to error propagation accumulated at each stage. We propose two non-cancellation multistage (NCMS) algorithms, referred to as NCMS-FKMA and NCMS-TSEA, that are free from the error propagation effects. Simulation results are presented to show that the NCMS-TSEA yields substantial performance gain compared with some existing blind separation algorithms, together with a computational complexity comparison. Finally, we draw some conclusions. [ABSTRACT FROM AUTHOR]

Recently, a novel maximum-likelihood sequence estimation (MLSE) equalizer was reported that avoids the explicit estimation of the channel impulse response. Instead, it is based on the fact that the (noise-free) channel outputs, needed by the Viterbi algorithm, coincide with the points around which the received (noisy) samples are clustered and can thus be estimated directly with the aid of a supervised clustering method. Moreover, this is achieved in a computationally efficient manner that exploits the channel linearity and the symmetries underlying the transmitted signal constellation. The resulting computational savings over the conventional MLSE equalization scheme are significant even in the case of relatively short channels where MLSE equalization is practically applicable. It was demonstrated, via simulations, that the performance of this algorithm is close to that using a least-squares (LS) channel estimator, although its computational complexity is even lower than that of the least-mean squares (LMS)-trained MLSE equalizer. This paper investigates the relationship of the center estimation (CE) part of the proposed equalizer with the LS method. It is proved that, when using LS with the training sequence employed by CE, the two methods lead to the same solution. However, when LS is trained with random data, it outperforms CE, with the performance difference being proportional to the channel length. A modified CE method, called MCE, is thus developed, that attains the performance of LS with perfectly random data, while still being much simpler computationally than classical LS estimation. Through the results of this paper, CE is confirmed as a method- ology that combines high performance, simplicity, and low computational cost, as required in a practical equalization task. An alternative, algebraic viewpoint on the CE method is also provided. [ABSTRACT FROM AUTHOR]

This paper proposes low-complexity constrained affine-projection (CAP) algorithms. The algorithms are suitable for linearly constrained filtering problems often encountered in communications systems. The CAP algorithms derived in this paper trade convergence speed and computational complexity in the same way as the conventional afilne-projection (AP) algorithm. In addition, data-selective versions of the CAP algorithm are derived based on the concept of set-membership filtering. The set-membership constrained affine-projection (SM-CAP) algorithms include several constraint sets in order to construct a space of feasible solutions for the coefficient updates. The SM-CAP algorithms include a data-dependent step size that provides fast convergence and low mean-squared error. The paper also discusses important aspects of convergence and stability of constrained normalized adaptation algorithms and shows that normalization may introduce bias in the final solution. [ABSTRACT FROM AUTHOR]

This paper considers the problem of simultaneous multiuser downlink beamforming. The idea is to employ a transmit antenna array to create multiple "beams" directed toward the individual users, and the aim is to increase throughput, measured by sum capacity. In particular, we are interested in the practically important case of more users than transmit antennas, which requires user selection. Optimal solutions to this problem can be prohibitively complex for online implementation at the base station and entail so-called Dirty Paper (DP) precoding for known interference. Suboptimal solutions capitalize on multiuser (selection) diversity to achieve a significant fraction of sum capacity at lower complexity cost. We analyze the throughput performance in Rayleigh fading of a suboptimal greedy DP-based scheme proposed by Tu and Blum. We also propose another user-selection method of he same computational complexity based on simple zero-forcing beamforming. Our results indicate that the proposed method attains a significant fraction of sum capacity and throughput of Tu and Blum's scheme and, thus, offers an attractive alternative to DP-based schemes. [ABSTRACT FROM AUTHOR]

The problem of finding the least-squares solution to a system of linear equations where the unknown vector is comprised of integers, but the matrix coefficient and given vector are comprised of real numbers, arises in many applications: communications, cryptography, GPS, to name a few. The problem is equivalent to finding the closest lattice point to a given point and is known to be NP-hard. In communications applications, however, the given vector is not arbitrary but rather is an unknown lattice point that has been perturbed by an additive noise vector whose statistical properties are known. Therefore, in this paper, rather than dwell on the worst-case complexity of the integer least-squares problem, we study its expected complexity, averaged over the noise and over the lattice. For the "sphere decoding" algorithm of Fincke and Pohst, we find a closed-form expression for the expected complexity, both for the infinite and finite lattice. It is demonstrated in the second part of this paper that, for a wide range of signal-to-noise ratios (SNRs) and numbers of antennas, the expected complexity is polynomial, in fact, often roughly cubic. Since many communications systems operate at noise levels for which the expected complexity turns out to be polynomial, this suggests that maximum-likelihood decoding, which was hitherto thought to be computationally intractable, can, in fact, be implemented in real time—a result with many practical implications. [ABSTRACT FROM AUTHOR]

Partial updating of LMS filter coefficients is an effective method for reducing computational load and power consumption in adaptive filter implementations. This paper presents an analysis of convergence of the class of Sequential Partial Update LMS algorithms (S-LMS) under various assumptions and shows that divergence can be prevented by scheduling coefficient updates at random, which we call the Stochastic Partial Update LMS algorithm (SPU-LMS). Specifically, under the standard independence assumptions, for wide sense stationary signals, the SSLMS algorithm converges in the mean if the step-size parameter μ is in the convergent range of ordinary LMS. Relaxing the independence assumption, it is shown that S-LMS and LMS algorithms have the same sufficient conditions for exponential stability. However, there exist nonstationary signals for which the existing algorithms, S-LMS included, are unstable and do not converge for any value of μ. On the other hand, under broad conditions, the SPU-LMS algorithm remains stable for nonstationary signals. Expressions for convergence rate and steady-state mean-square error of SPU.LMS are derived. The theoretical results of this paper are validated and compared by simulation through numerical examples. [ABSTRACT FROM AUTHOR]

We study the problem of power efficient multiuser beamforming transmission for both uplink and downlink. The base station is equipped with multiple antennas, whereas the mobile units have single antennas. In the uplink, interference is canced by successive decoding. in the downlink, ideal "dirty paper" precoding is assumed. The design goal is to minimize the total transmit power while maintaining individual SINR constraints. In the uplink, the optimization problem is solved by a recursive formula with low computational complexity. The downlink problem is solved by exploiting the duality between uplink and downlink; thus, the uplink solution carries over to the downlink. In the second part of the paper, we show how the solution can be applied to the problem of rate balancing in Gaussian multiuser channels. We propose a strategy for throughput-wise optimal transmission for broadcast and multiple access channels under a sum power constraint. Finally, we show that single-user transmission achieves the sum capacity in the low-SNR regime. We completely characterize the SNR-range where single-user transmission is optimal. [ABSTRACT FROM AUTHOR]

Decimation and interpolation are very common multirate signal processing operations. Conventional decimation or interpolation technique using polyphase filters has the advantage that for a given transition-band sharpness, the filter's computational complexity decreases with increasing interpolation or decimation factor. Nevertheless, if the transition band of the decimation or interpolation filter is very sharp, the complexity of the filter may still be very high. The complexity of a very sharp filter may be reduced using the frequency-response masking (FRM) technique. However, as shown in this paper, for a given transition-band sharpness, the computational complexity of the classical FRM method does not reduce as rapidly as the increase in decimation or interpolation factor. In this paper, we present a novel variant of the FRM technique for interpolation or decimation application. In this new variant, the computational complexity reduces as rapidly as the interpolation or decimation factor increases. The reduction in computational complexity increases with decreasing transition width. Over an order of magnitude reduction in computational complexity is achieved when compared with conventional polyphase approach in a particular example presented in this paper. [ABSTRACT FROM AUTHOR]

The fast Fourier transform (FFT) is an essential tool in digital signal processing and communication. In the applications of the FFT where the required outputs are very sparse, for example, in digital filtering, one may only require the spectrum corresponding to certain bins of the FFT or in narrow frequency windows. In these cases, most of the FFT outputs are not required. Some pruning algorithms have been proposed to deal with such cases. However, most of the pruning algorithms require that the outputs be in continuous windows. This paper develops a traced FFT Pruning method (TFFTP), which is a novel technique and does not require this condition. Under some circumstances, considerable savings in computational complexity and power consumption can be realized using the TFFTP compared to the FFT. This paper derives the average number of butterflies that need to be executed when only kin input or/and kout output bins of an N point FFT, where kin ≤ N, or/and kout ≤ N are required. This method is then extended to arbitrary radix FFT pruning and simultaneous input and output pruning case. [ABSTRACT FROM AUTHOR]

Most adaptive filtering algorithms couple performance with complexity. Over the last 15 years, a class of algorithms, termed "affine projection" algorithms, have given system designers the capability to tradeoff performance with complexity. By changing parameters and the size/scale of data used to update the coefficients of an adaptive filter but without fundamentally changing the algorithm structure, a system designer can radically change the performance of the adaptive algorithm. This paper discusses low-complexity data reusing algorithms that are closely related to affine projection algorithms. This paper presents various low-complexity and highly flexible schemes for improving convergence rates of adaptive algorithms that utilize data reusing strategies. All of these schemes are unified by a row. projection framework in existence for more than 65 years. This framework leads to the classification of all data reusing and affine projection methods for adaptive filtering into two categories: the Kaczmarz and Cimmino methods. Simulation and convergence analysis results are presented for these methods under a number of conditions. They are compared in terms of convergence rate performance and computational complexity. [ABSTRACT FROM AUTHOR]

This paper considers the coherent integration problem for a maneuvering target with complex motions, where the velocity, acceleration, and jerk result in respectively the first-order range migration (FRM), second-order range migration (SRM), and third-order range migration (TRM) within the coherent pulse interval. A new coherent integration algorithm based on generalized keystone transform (KT) and second-order dechirp process is proposed, which employs the third-order KT, six-order KT, second-order KT, and fold factor searching to correct the TRM, SRM, and FRM, respectively. The range migration change during each step and computational complexity are also theoretically analyzed. Compared with the generalized Radon Fourier transform (GRFT) algorithm, the presented method can avoid the blind speed sidelobe (BSSL) and acquire close integration performance but with much lower computational cost. Simulations are provided to demonstrate the effectiveness. Finally, a generalized method, named generalized KT and generalized dechirp process (GKTGDP), is also introduced for the maneuvering target with arbitrary high-order range migration. [ABSTRACT FROM PUBLISHER]

Identification of systems with sparse impulse response encounters large applicability. Numerous techniques have been proposed to identify such systems efficiently. One strategy that leads to specially good results is to detect the active (nonzero) response samples and update only the corresponding adaptive coefficients. Wavelet-based approaches have been shown to be specially effective to this end. This paper proposes a new region-based wavelet-packet (RBWP) algorithm for efficient identification of systems with sparse impulse responses with arbitrary frequency spectra and with any delay of the effective response. The discrete wavelet packet transform (DWPT) is adaptively tailored to the energy distribution of the unknown system's response spectrum. The new algorithm leads to a reduced number of active weights and to a reduced computational complexity, when compared with competing wavelet-based algorithms. Monte Carlo simulation results show good performances regarding convergence speed and robustness to design parameter choice. [ABSTRACT FROM PUBLISHER]

This paper studies optimal transmission over wireless channels with imperfect channel state information available at the transmitter side in the context of point-to-point channels, multiuser orthogonal frequency division multiplexing, and random access. Terminals adapt transmitted power and coding mode to channel estimates in order to maximize expected throughput subject to average power constraints. To reduce the likelihood of packet losses due to the mismatch between channel estimates and actual channel values, a backoff function is further introduced to enforce the selection of more conservative coding modes. Joint determination of optimal power allocations and backoff functions is a nonconvex stochastic optimization problem with infinitely many variables that despite its lack of convexity is part of a class of problems with null duality gap. Exploiting the resulting equivalence between primal and dual problems, we show that optimal power allocations and channel backoff functions are uniquely determined by optimal dual variables. This affords considerable simplification because the dual problem is convex and finite dimensional. We further exploit this reduction in computational complexity to develop iterative algorithms to find optimal operating points. These algorithms implement stochastic subgradient descent in the dual domain and operate without knowledge of the probability distribution of the fading channels. Numerical results corroborate theoretical findings. [ABSTRACT FROM PUBLISHER]

Bayesian filtering is a statistical approach that naturally appears in many signal processing problems. Ranging from Kalman filter to particle filters, there is a plethora of alternatives depending on model assumptions. With the exception of very few tractable cases, one has to resort to suboptimal methods due to the inability to analytically compute the Bayesian recursion in general dynamical systems. This is why it has attracted the attention of many researchers in order to develop efficient algorithms to implement it. We focus our interest into a recently developed algorithm known as the Quadrature Kalman filter (QKF). Under the Gaussian assumption, the QKF can tackle arbitrary nonlinearities by resorting to the Gauss-Hermite quadrature rules. However, its complexity increases exponentially with the state-space dimension. In this paper we study a complexity reduction technique for the QKF based on the partitioning of the state-space, referred to as the Multiple QKF. We prove that partitioning schemes can effectively be used to reduce the curse of dimensionality in the QKF. Simulation results are also provided to show that a nearly-optimal performance can be attained, while drastically reducing the computational complexity with respect to state-of-the-art algorithms that are able to deal with such nonlinear filtering problems. [ABSTRACT FROM PUBLISHER]

As a greedy algorithm to recover sparse signals from compressed measurements, orthogonal matching pursuit (OMP) algorithm has received much attention in recent years. In this paper, we introduce an extension of the OMP for pursuing efficiency in reconstructing sparse signals. Our approach, henceforth referred to as generalized OMP (gOMP), is literally a generalization of the OMP in the sense that multiple N indices are identified per iteration. Owing to the selection of multiple “correct” indices, the gOMP algorithm is finished with much smaller number of iterations when compared to the OMP. We show that the gOMP can perfectly reconstruct any K-sparse signals (K>1), provided that the sensing matrix satisfies the RIP with \deltaNK<{{\sqrt{N}}\over{\sqrt{K}+3\sqrt{N}}}. We also demonstrate by empirical simulations that the gOMP has excellent recovery performance comparable to \ell1-minimization technique with fast processing speed and competitive computational complexity. [ABSTRACT FROM PUBLISHER]

This paper exemplifies that the use of multiple kernels leads to efficient adaptive filtering for nonlinear systems. Two types of multikernel adaptive filtering algorithms are proposed. One is a simple generalization of the kernel normalized least mean square (KNLMS) algorithm refid="ref2"/ , adopting a coherence criterion for dictionary designing. The other is derived by applying the adaptive proximal forward-backward splitting method to a certain squared distance function plus a weighted block \ell1 norm penalty, encouraging the sparsity of an adaptive filter at the block level for efficiency. The proposed multikernel approach enjoys a higher degree of freedom than those approaches which design a kernel as a convex combination of multiple kernels. Numerical examples show that the proposed approach achieves significant gains particularly for nonstationary data as well as insensitivity to the choice of some design-parameters. [ABSTRACT FROM PUBLISHER]

Weighted median filters are increasingly being used in signal processing applications and thus fast implementations are of importance. This paper introduces a fast algorithm to compute the weighted median (WM) of N samples which has linear time and space complexity as opposed to O(N log N) which is the time complexity of traditional sorting algorithms. A popular selection algorithm often used to find the WM in large data sets is Quickselect whose performance is highly dependent on how the pivots are chosen. We introduce an optimization based pivot selection strategy which results in significantly improved performance as well as a more consistent runtime compared to traditional approaches. The selected pivots are order statistics of subsets. In order to find the optimal order statistics as well as the optimal subset sizes, a set of cost functions are derived, which when minimized lead to optimal design parameters. We compare the complexity to Floyd and Rivest's algorithm SELECT which to date has been the fastest median finding algorithm and we show that the proposed algorithm compared with SELECT requires close to 30% fewer comparisons. It is also shown that the proposed selection algorithm is asymptotically optimal for large N. [ABSTRACT FROM PUBLISHER]

We consider the problem of compressed sensing and propose new deterministic low-storage constructions of compressive sampling matrices based on classical finite-geometry generalized polygons. For the noiseless measurements case, we develop a novel exact-recovery algorithm for strictly sparse signals that utilizes the geometry properties of generalized polygons and exhibits complexity that depends on the sparsity value only. In the presence of measurement noise, recovery of the generalized-polygon sampled signals can be carried out effectively using a belief propagation algorithm. Experimental studies included in this paper illustrate our theoretical developments. [ABSTRACT FROM PUBLISHER]

This paper considers iterative detection of bit-interleaved coded continuous phase modulation in the presence of both phase noise (PN) and additive white Gaussian noise (AWGN). The proposed receiver iterates between a detection module and an estimation module. The detection module operates according to the sum-product algorithm and the factor graph framework in order to perform coherent maximum a posteriori bit detection in AWGN, using a PN estimate provided by the estimation module. The latter module, which results from the expectation-maximization algorithm for maximum likelihood estimation of the unknown PN samples, is implemented as a smoothing phase-locked loop that uses soft decisions provided by the detector. The separation between the detection and the estimation modules allows the use of an off-the-shelf (coherent) bit detector. The technique is further characterized by a very low computational complexity, a small error performance degradation and a small number of overhead symbols. [ABSTRACT FROM AUTHOR]

This paper presents computationally efficient implementations for several recent algorithms based on the iterative adaptive approach (IAA) for uniformly sampled one- and two-dimensional data sets, considering both the complete data case, and the cases when the data sets are missing samples, either lacking arbitrary locations, or having gaps or periodically reoccurring gaps. By exploiting the method's inherent low displacement rank, together with the development of suitable Gohberg–Semencul representations, and the use of data dependent trigonometric polynomials, the proposed implementations are shown to offer a reduction of the necessary computational complexity by at least one order of magnitude. Numerical simulations together with theoretical complexity measures illustrate the achieved performance gain. [ABSTRACT FROM AUTHOR]

In this paper, an enhanced linear minimum mean square error (LMMSE) turbo equalization scheme is proposed for multiple-input multiple-output (MIMO) communication systems with bit-interleaved coded modulation (BICM) in the time domain and multiplexing in the space domain. The proposed turbo equalization scheme outperforms the conventional LMMSE turbo equalization by adopting two new signal processing techniques. First, it performs hybrid soft interference cancellation (HSOIC) by subtracting the soft decisions of the interfering symbols, and the soft decisions are calculated by using a hybrid of the a priori information at the equalizer input and the a posteriori information at the equalizer output. Second, it employs a novel block-wise reliability-based ordering scheme such that more “reliable” symbols are detected before the less “reliable” ones to reduce error propagation in HSOIC. The symbol reliability information is based on the symbol a priori probability, as a unique byproduct of turbo detection, thus can be obtained with very small overhead. A low-complexity approximation of the enhanced MIMO LMMSE turbo equalization is also proposed to balance the tradeoff between complexity and performance. The performance of the enhanced MIMO LMMSE turbo equalization has been verified through both numerical simulations and the undersea experimental data collected in the SPACE08 experiment launched near Martha's Vineyard, Edgartown, MA, in 2008. [ABSTRACT FROM PUBLISHER]

In this paper, we study an approach to the processing of radar signals motivated by the neural processing of echolocation waveforms by certain species of bats. We propose a transmission strategy and a corresponding family of processing algorithms and study the resulting delay-Doppler resolution characteristics. We investigate both the improvement in delay-Doppler resolution and the generation of artifacts in the delay-Doppler maps generated by this approach. Because the resulting schemes are not optimal for detection, we investigate the degradation in detection performance when compared to the matched filter. The contribution of the proposed scheme is a significant improvement in delay-Doppler resolution without a significant increase in system or computational complexity or a significant degradation in detection performance. [ABSTRACT FROM AUTHOR]

In this paper, we consider a wireless amplify-and-forward relay network with one relay node and multiple source-destination pairs/users and propose a pricing framework that enables the relay to set prices to maximize either its revenue or any desirable system utility. Specifically, depending on the quality of the received signals, the relay sets prices and correspondingly charges the users utilizing its resources for their transmissions. The price is determined in such a way that the relay's revenue or system utility is maximized. Given the specified price, the users competitively employ the relay node to forward their signals. We model each user as a rational player, which aims at maximizing its own net utility through power allocation, and analyze the competition among the users within the framework of noncooperative game theory. It is shown that, in the game played by the users, there always exists a unique pure Nash equilibrium point that can be achieved through distributed iterations. Next, subject to the availability of complete information about the users at the relay, we propose a low-complexity uniform pricing algorithm and an optimal differentiated pricing algorithm, in which the relay either charges the users at a suboptimal uniform price or charges different users at different prices. We also show that, by applying the differentiated pricing algorithm that enforces the users to transmit at certain power levels, any system utility can be maximized. Extensive simulations are conducted to quantify the performance of the proposed methods. [ABSTRACT FROM AUTHOR]

In this paper, low-complexity joint power assignment algorithms are developed for multi-source multi-destination relay networks where multiple sources share a common relay that forwards all received signals simultaneously to destinations. In particular, we consider the following power optimization strategies: (i) Minimization of the total transmission power of the sources and the relay under the constraint that the signal-to-interference-plus-noise ratio (SINR) requirement of each source-destination pair is satisfied, and (ii) Maximization of the minimum SINR among all source-destination pairs subject to any given total power budget. Both optimization problems involve K power variables, where K is the number of source-destination pairs in the network, and an exhaustive search is prohibitive for large K. In this work, we develop a methodology that allows us to obtain an asymptotically tight approximation of the SINR and reformulate the original optimization problems to single-variable optimization problems, which can be easily solved by numerical search of the single variable. Then, the corresponding optimal transmission power at each source and relay can be calculated directly. The proposed optimization schemes are scalable and lead to power assignment algorithms that exhibit the same optimization complexity for any number (K) of source-destination pairs in the network. Moreover, we apply the methodology that we developed to solve a related max-min SINR based optimization problem in which we determine power assignment for the sources and the relay to maximize the minimum SINR among all source-destination pairs subject to any given total power budget. Extensive numerical studies illustrate and validate our theoretical developments. [ABSTRACT FROM AUTHOR]