Weighted LASSO for Sparse Recovery With Statistical Prior Support Information

Lian, Lixiang; Liu, An; Lau, Vincent K. N.

doi:10.1109/tsp.2018.2791949

Cited by 29 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2) Standard LASSO: The channel is recovered by solving the convex optimization problem (5). Standard LASSO estimates the channel without exploiting the burst sparsity property [24], [27]. 3) Burst LASSO: In this approach, standard LASSO is modified by using a lifting transformation to convert the burst sparsity to the block model [13], [25].…”

Section: Numerical Resultsmentioning

confidence: 99%

“…The challenge yet to be overcome is that these algorithms have been developed for certain special cases of massive MIMO channels, e.g., where the users' channels share the same scatterers in the propagation environment or the same sparsity pattern in the sub-channels, properties that may not hold in many scenarios. Another direction taken in the literature [22]- [24] is to improve CS-based methods by exploiting partial support information. In all these works, the channel recovery problem is formulated as a weighted linear optimization problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A burst-form CSI estimation approach for FDD massive MIMO systems

2019

View full text Add to dashboard Cite

Pilot and channel state information (CSI) feedback overhead in the downlink and uplink paths are two major implementation challenges in frequency-division duplex (FDD) based massive MIMO systems. When the massive MIMO channel satisfies the burst-sparsity property, we can acquire the channel with compressed pilots and CSI feedback in a more efficient approach. This paper proposes a burst-form estimation approach, referred to as the burst-form least squares (BFLS) algorithm, to fully utilize the burst-sparsity property of massive MIMO channels. The proposed algorithm is based on knowledge of the starting location of each burst at the user side. For situations where the starting locations change quickly or are otherwise initially unknown at the user, a starting point estimation (SPE) algorithm is proposed to provide the position of each burst in the channel vector. Numerical results demonstrate that the BFLS algorithm acquires the channel better than competing approaches and reaches the performance upper bound. It is shown that the SPE algorithm can find the location of bursts with high accuracy and using the estimated values do not significantly degrade the estimation quality.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A burst-form CSI estimation approach for FDD massive MIMO systems

2019

View full text Add to dashboard Cite

show abstract

“…We note that Lian, et al recently studied (4) from both theoretical and experimental aspects in [28],…”

Section: Introductionmentioning

confidence: 89%

Deterministic Analysis of Weighted BPDN With Partially Known Support Information

Wang,

Wang

2019

Preprint

View full text Add to dashboard Cite

In this paper, with the aid of the powerful Restricted Isometry Constant (RIC), a deterministic (or say non-stochastic) analysis, which includes a series of sufficient conditions (related to the RIC order) and their resultant error estimates, is established for the weighted Basis Pursuit De-Noising (BPDN) to guarantee the robust signal recovery when Partially Known Support Information (PKSI) of the signal is available. Specifically, the obtained conditions extend nontrivially the ones induced recently for the traditional constrained weighted ℓ 1 -minimization model to those for its unconstrained counterpart, i.e., the weighted BPDN. The obtained error estimates are also comparable to the analogous ones induced previously for the robust recovery of the signals with PKSI from some constrained models. Moreover, these results to some degree may well complement the recent investigation of the weighted BPDN which is based on the stochastic analysis.

show abstract

“…Comparing with other model selection methods such as the least absolute shrinkage and selection operator (LASSO) method [27], the LARS method is more stable and computationally efficient. Nevertheless, there are some factors that may negatively influence the performance of the LARS method with respect to the accuracy and the stability.…”

Section: The Adaptive Lars Methods 1) the Potential Problems Of The Lars Methodmentioning

confidence: 99%

An Adaptive Least Angle Regression Method for Uncertainty Quantification in FDTD Computation

Monebhurrun

Himeno

et al. 2018

IEEE Trans. Antennas Propagat.

View full text Add to dashboard Cite

The non-intrusive polynomial chaos (NIPC) expansion method is used to quantify the uncertainty of a stochastic system. It potentially reduces the number of numerical simulations in modelling process, thus improving efficiency, whilst ensuring accuracy. However, the number of polynomial bases grows substantially with the increase of random parameters, which may render the technique ineffective due to the excessive computational resources. To address such problems, methods based on the sparse strategy such as the least angle regression (LARS) method with hyperbolic index sets can be used. This paper presents the first work to improve the accuracy of the original LARS method for uncertainty quantification (UQ). We propose an adaptive LARS method in order to quantify the uncertainty of the results from the numerical simulations with higher accuracy than the original LARS method. The proposed method outperforms the original LARS method in terms of accuracy and stability. The L2 regularisation scheme further reduces the number of input samples while maintaining the accuracy of the LARS method.Index Terms-Non-intrusive polynomial chaos (NIPC) expansion, least angle regression (LARS), uncertainty quantification (UQ), finite difference time domain (FDTD), Debye media

show abstract

Weighted LASSO for Sparse Recovery With Statistical Prior Support Information

Cited by 29 publications

References 16 publications

A burst-form CSI estimation approach for FDD massive MIMO systems

A burst-form CSI estimation approach for FDD massive MIMO systems

Deterministic Analysis of Weighted BPDN With Partially Known Support Information

An Adaptive Least Angle Regression Method for Uncertainty Quantification in FDTD Computation

Contact Info

Product

Resources

About