Results 1  10
of
19
Gaussian belief propagation solver for systems of linear equations
 in IEEE Int. Symp. on Inform. Theory (ISIT
, 2008
"... Abstract — The canonical problem of solving a system of linear equations arises in numerous contexts in information theory, communication theory, and related fields. In this contribution, we develop a solution based upon Gaussian belief propagation (GaBP) that does not involve direct matrix inversio ..."
Abstract

Cited by 18 (9 self)
 Add to MetaCart
Abstract — The canonical problem of solving a system of linear equations arises in numerous contexts in information theory, communication theory, and related fields. In this contribution, we develop a solution based upon Gaussian belief propagation (GaBP) that does not involve direct matrix inversion. The iterative nature of our approach allows for a distributed messagepassing implementation of the solution algorithm. We also address some properties of the GaBP solver, including convergence, exactness, its maxproduct version and relation to classical solution methods. The application example of decorrelation in CDMA is used to demonstrate the faster convergence rate of the proposed solver in comparison to conventional linearalgebraic iterative solution methods. Solving a system of linear equations Ax = b is one of
Gaussian belief propagation based multiuser detection
 in IEEE Int. Symp. Inform. Theory (ISIT
, 2008
"... Abstract — In this work, we present a novel construction for solving the linear multiuser detection problem using the Gaussian Belief Propagation algorithm. Our algorithm yields an efficient, iterative and distributed implementation of the MMSE detector. Compared to our previous formulation, the new ..."
Abstract

Cited by 17 (14 self)
 Add to MetaCart
Abstract — In this work, we present a novel construction for solving the linear multiuser detection problem using the Gaussian Belief Propagation algorithm. Our algorithm yields an efficient, iterative and distributed implementation of the MMSE detector. Compared to our previous formulation, the new algorithm offers a reduction in memory requirements, the number of computational steps, and the number of messages passed. We prove that a detection method recently proposed by Montanari et al. is an instance of ours, and we provide new convergence results applicable to both. I.
Linear Detection via Belief Propagation
 In the 45th Annual Allerton Conference on Communication, Control, and Computing, Allerton
"... Abstract — In this paper, the paradigm of linear detection is reformulated as a Gaussian belief propagation (GaBP) scheme, without resorting to direct matrix inversion. The derived iterative framework allows for a distributive messagepassing implementation of this important class of suboptimal tra ..."
Abstract

Cited by 12 (11 self)
 Add to MetaCart
Abstract — In this paper, the paradigm of linear detection is reformulated as a Gaussian belief propagation (GaBP) scheme, without resorting to direct matrix inversion. The derived iterative framework allows for a distributive messagepassing implementation of this important class of suboptimal tractable estimators. The properties of GaBPbased linear detection are addressed, while its faster convergence, in comparison with conventional iterative solution methods, is demonstrated experimentally. I.
Speed and accuracy comparison of techniques for multiuser detection in synchronous CDMA
 COMMUNICATIONS WITH THE IEEE VEHICULAR TECHNOLOGY SOCIETY. LEE FREITAG (M’88) RECEIVED THE B.S. AND M.S. DEGREES IN ELECTRICAL ENGINEERING FROM THE UNIVERSITY OF ALASKA, FAIRBANKS, IN 1986 AND
, 2004
"... In this letter, we compare the complexity and efficiency of several methods used for multiuser detection in a synchronous codedivision multipleaccess system. Various methods are discussed, including decisionfeedback (DF) detection, group decisionfeedback (GDF) detection, coordinate descent, qua ..."
Abstract

Cited by 9 (1 self)
 Add to MetaCart
In this letter, we compare the complexity and efficiency of several methods used for multiuser detection in a synchronous codedivision multipleaccess system. Various methods are discussed, including decisionfeedback (DF) detection, group decisionfeedback (GDF) detection, coordinate descent, quadratic programming with constraints, spacealternating generalized EM (SAGE) detection, Tabu search, a Boltzmann machine detector, semidefinite relaxation, probabilistic data association (PDA), branch and bound (BBD), and the sphere decoding (SD) method. The efficiencies of the algorithms, defined as the probability of group detection error divided by the number of floating point computations, are compared under various situations. Of particular interest is the appearance of an “efficient frontier ” of algorithms, primarily composed of DF detector, GDF detector, PDA detector, the BBD optimal algorithm, and the SD method. The efficient frontier is the convex hull of algorithms as plotted on probability of error versus computational demands axes: algorithms not on this efficient frontier can be considered dominated by those that are.
Large System Analysis of Linear Multistage Parallel Interference Cancellation
 IEEE Transactions on Communications
, 2002
"... In this paper, we derive an expression for the signal to interferenceplusnoise ratio of a linear multistage parallel interference cancellation receiver. We focus on a linear multistage receiver which converges to the linear minimum meansquared error receiver as the number of stages increases. The ..."
Abstract

Cited by 8 (3 self)
 Add to MetaCart
In this paper, we derive an expression for the signal to interferenceplusnoise ratio of a linear multistage parallel interference cancellation receiver. We focus on a linear multistage receiver which converges to the linear minimum meansquared error receiver as the number of stages increases. The signal to interference plusnoise ratio is given in terms of the system loading, the partial cancellation factor, the number of stages, and the signaltonoise ratio. Our expression also allows a simple approximation for the bit error rate at each stage. Finally, we perform a numerical optimization to maximize the signal to interferenceplusnoise ratio expression with respect to the partial cancellation factor of the resulting linear multistage receiver.
Hidden convexity based near maximumlikelihood CDMA detection
 IN PROC. 39TH ANNU. CONF. INFORMATION SCIENCES SYSTEMS (CISS
, 2005
"... ..."
Constrained detection for noncoherent nonlinear multiuser communications
 In Proceedings of 34th Asilomar Conference on Signals, Systems and Computers
, 2000
"... sinhar @ winlab.rutgers.edu yener @ eecs.lehigh.edu ryates @ winlab.rutgers.edu We consider noncoherent multiuser detection techniques for a system with users employing nonlinear modulation using nonorthogonal signals. Our aim is to investigate nearoptimum noncoherent multiuser detection techniques ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
sinhar @ winlab.rutgers.edu yener @ eecs.lehigh.edu ryates @ winlab.rutgers.edu We consider noncoherent multiuser detection techniques for a system with users employing nonlinear modulation using nonorthogonal signals. Our aim is to investigate nearoptimum noncoherent multiuser detection techniques that utilize the structure of the received signuls while retaining reasonable complexity. We explore detectors that are derived using nonlinear programming approximations of the maximum likelihood multiuser detector as well as soft interference cancellers. We also propose a class of detectors called the partial detectors which improve the perfomnce of the decorrelator and MMSE type detectors. We evaluate the proposed detectors ’ performunce to provide numerical comparisons. I.
Multiuser detection using the Taguchi method for the DSCDMA systems
 IEEE Trans. Wireless Commun
"... Abstract—We study multiuser detection for directsequence codedivision multipleaccess systems in a multipath environment. Systems with unknown channel information are considered and the wellknown result for maximum likelihood multiuser detector is directly used in our work. Due to the high comput ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
Abstract—We study multiuser detection for directsequence codedivision multipleaccess systems in a multipath environment. Systems with unknown channel information are considered and the wellknown result for maximum likelihood multiuser detector is directly used in our work. Due to the high computational cost of the maximum likelihood detector, most existing works have investigated simplified, linearized, and/or suboptimal solutions that have less computational requirements. In our approach, we use the Taguchi method that involves the use of orthogonal arrays in estimating the gradient of the likelihood function. The Taguchi method has been widely used in experimental designs for problems with multiple parameters where the optimization of a cost function is required. In this work, we choose the likelihood function as the cost function in the Taguchi method. The use of the Taguchi method for multiuser detection is a novel idea, and it leads to efficient algorithms that can find a satisfactory solution by maximizing the likelihood function in a small number of iterations. One of the advantages of the present Taguchi method is that it is blind since no channel estimation is required to detect the transmitted data, which is not the case in many existing methods. Simulation results show that the Taguchi multiuser detector significantly outperforms the conventional receivers, is insensitive to initial values of parameters, and has performance close to that of minimum mean square error detectors and decorrelating detectors. In addition, our algorithm is suitable for parallel implementations. Index Terms—Directsequence codedivision multipleaccess (DSCDMA), maximum likelihood, multiuser detection, orthogonal
Generalized Feedback Detection for Spatial Multiplexing MultiAntenna Systems
"... Abstract — We present a unified detection framework for spatial multiplexing multipleinput multipleoutput (MIMO) systems by generalizing Heller’s classical feedback decoding algorithm for convolutional codes. The resulting generalized feedback detector (GFD) is characterized by three parameters: w ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
Abstract — We present a unified detection framework for spatial multiplexing multipleinput multipleoutput (MIMO) systems by generalizing Heller’s classical feedback decoding algorithm for convolutional codes. The resulting generalized feedback detector (GFD) is characterized by three parameters: window size, step size and branch factor. Many existing MIMO detectors are turned out to be special cases of the GFD. Moreover, different parameter choices can provide various performancecomplexity tradeoffs. The connection between MIMO detectors and tree search algorithms is also established. To reduce redundant computations in the GFD, a shared computation technique is proposed by using a tree data structure. Using a union bound based analysis of the symbol error rates, the diversity order and signaltonoise ratio (SNR) gain are derived analytically as functions of the three parameters; for example, the diversity order of the GFD varies between 1 and N. The complexity of the GFD varies between those of the maximumlikelihood (ML) detector and the zeroforcing decision feedback detector (ZFDFD). Extensive computer simulation results are also provided. Index Terms — MIMO, feedback decoding, decision feedback detector.
Inference with Multivariate HeavyTails in Linear Models
"... Heavytailed distributions naturally occur in many real life problems. Unfortunately, it is typically not possible to compute inference in closedform in graphical models which involve such heavytailed distributions. In this work, we propose a novel simple linear graphical model for independent lat ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
Heavytailed distributions naturally occur in many real life problems. Unfortunately, it is typically not possible to compute inference in closedform in graphical models which involve such heavytailed distributions. In this work, we propose a novel simple linear graphical model for independent latent random variables, called linear characteristic model (LCM), defined in the characteristic function domain. Using stable distributions, a heavytailed family of distributions which is a generalization of Cauchy, Lévy and Gaussian distributions, we show for the first time, how to compute both exact and approximate inference in such a linear multivariate graphical model. LCMs are not limited to stable distributions, in fact LCMs are always defined for any random variables (discrete, continuous or a mixture of both). We provide a realistic problem from the field of computer networks to demonstrate the applicability of our construction. Other potential application is iterative decoding of linear channels with nonGaussian noise. 1