We consider the problem of sparse channel estimation in massive multiple-input multiple-output systems. In this context, we propose an enhanced version of the sparse Bayesian learning (SBL) framework, referred to as enhanced SBL (E-SBL), which is based on a reparameterization of the original SBL model. Specifically, we introduce a scale vector that brings extra flexibility to the model, which is estimated along with the other unknowns. Moreover, we introduce a variant of E-SBL, referred to as modified E-SBL (M-E-SBL), which is based on a computationally more efficient parameter estimation. We compare the proposed E-SBL and M-E-SBL with the baseline SBL and with a method based on variational message passing (VMP) in terms of computational complexity and performance. Numerical results show that the proposed E-SBL and M-E-SBL outperform the baseline SBL and VMP in terms of mean squared error of the channel estimation in all the considered scenarios. Furthermore, we show that M-E-SBL produces results comparable with E-SBL with considerably cheaper computations.

Abstract. Inverse problems are in many cases solved with optimization techniques. When the underlying model is linear, first-order gradient methods are usually sufficient. With nonlinear models, due to nonconvexity, one must often resort to second-order methods that are computationally more expensive. In this work we aim to approximate a nonlinear model with a linear one and correct the resulting approximation error. We develop a sequential method that iteratively solves a linear inverse problem and updates the approximation error by evaluating it at the new solution. This treatment convexifies the problem and allows us to benefit from established convex optimization methods. We separately consider cases where the approximation is fixed over iterations and where the approximation is adaptive. In the fixed case we show theoretically under what assumptions the sequence converges. In the adaptive case, particularly considering the special case of approximation by first-order Taylor expansion, we show that with certain assumptions the sequence converges to a critical point of the original nonconvex functional. Furthermore, we show that with quadratic objective functions the sequence corresponds to the Gauss–Newton method. Finally, we showcase numerical results superior to the conventional model correction method. We also show that a fixed approximation can provide competitive results with considerable computational speed-up.

MOTIVATION: Improved DNA technology has made it practical to estimate single-nucleotide polymorphism (SNP)-heritability among distantly related individuals with unknown relationships. For growth- and development-related traits, it is meaningful to base SNP-heritability estimation on longitudinal data due to the time-dependency of the process. However, only few statistical methods have been developed so far for estimating dynamic SNP-heritability and quantifying its full uncertainty. RESULTS: We introduce a completely tuning-free Bayesian Gaussian process (GP)-based approach for estimating dynamic variance components and heritability as their function. For parameter estimation, we use a modern Markov Chain Monte Carlo method which allows full uncertainty quantification. Several datasets are analysed and our results clearly illustrate that the 95% credible intervals of the proposed joint estimation method (which 'borrows strength' from adjacent time points) are significantly narrower than of a two-stage baseline method that first estimates the variance components at each time point independently and then performs smoothing. We compare the method with a random regression model using MTG2 and BLUPF90 software and quantitative measures indicate superior performance of our method. Results are presented for simulated and real data with up to 1000 time points. Finally, we demonstrate scalability of the proposed method for simulated data with tens of thousands of individuals. AVAILABILITY AND IMPLEMENTATION: The C++ implementation dynBGP and simulated data are available in GitHub: https://github.com/aarjas/dynBGP. The programmes can be run in R. Real datasets are available in QTL archive: https://phenome.jax.org/centers/QTLA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.