The widespread adoption of artificial intelligence (AI) in next-generation communication systems is challenged by the heterogeneity of traffic and network conditions, which call for the use of highly contextual, site-specific, data. A promising solution is to rely not only on real-world data, but also on synthetic pseudo-data generated by a network digital twin (NDT). However, the effectiveness of this approach hinges on the accuracy of the NDT, which can vary widely across different contexts. To address this problem, this paper introduces contextaware doubly-robust (CDR) learning, a novel semi-supervised scheme that adapts its reliance on the pseudo-data to the different levels of fidelity of the NDT across contexts. CDR is evaluated on the task of downlink beamforming where it outperforms previous state-of-the-art approaches, providing a 24% loss decrease when compared to doubly-robust (DR) semi-supervised learning in regimes with low labeled data availability.

Cell-free massive MIMO is emerging as a promising technology for future wireless communication systems, which is expected to offer uniform coverage and high spectral efficiency compared to classical cellular systems. We study in this paper how cell-free massive MIMO can support federated edge learning. Taking advantage of the additive nature of the wireless multiple access channel, over-the-air computation is exploited, where the clients send their local updates simultaneously over the same communication resource. Such an approach, known as over-the-air federated learning (OTA-FL), is proven to alleviate the communication overhead of federated learning over wireless networks. Considering channel correlation and only imperfect channel state information available at the central server, we propose a practical implementation of OTA-FL over cell-free massive MIMO. The convergence of the proposed implementation is studied analytically and experimentally, confirming the benefits of cell-free massive MIMO for OTA-FL.

Deep learning has been widely adopted for channel state information (CSI)-fingerprinting indoor localization systems. These systems usually consist of two main parts,${i}$.${e}$., a positioning network that learns the mapping from high-dimensional CSI to physical locations and a tracking system that utilizes historical CSI to reduce the positioning error. This paper presents a new localization system with high accuracy and generality. On the one hand, the receptive field of the existing convolutional neural network (CNN)-fingerprinting positioning networks is limited, restricting their performance as useful information in CSI is not explored thoroughly. As a solution, we propose a novel attention-augmented residual CNN to utilize the local information and global context in CSI exhaustively. On the other hand, considering the generality of a tracking system, we decouple the tracking system from the CSI environments so that one tracking system for all environments becomes possible. Specifically, we remodel the tracking problem as a denoising task and solve it with deep trajectory prior. Furthermore, we investigate how the precision difference of inertial measurement units will adversely affect the tracking performance and adopt plug-and-play to solve the precision difference problem. Experiments show the superiority of our methods over existing approaches in performance and generality improvement.

In this paper, we study the hard and soft support vector regression techniques applied to a set of $n$ linear measurements of the form $y_i=\boldsymbol{\beta}_\star^{T}{\bf x}_i +n_i$ where $\boldsymbol{\beta}_\star$ is an unknown vector, $\left\{{\bf x}_i\right\}_{i=1}^n$ are the feature vectors and $\left\{{n}_i\right\}_{i=1}^n$ model the noise. Particularly, under some plausible assumptions on the statistical distribution of the data, we characterize the feasibility condition for the hard support vector regression in the regime of high dimensions and, when feasible, derive an asymptotic approximation for its risk. Similarly, we study the test risk for the soft support vector regression as a function of its parameters. Our results are then used to optimally tune the parameters intervening in the design of hard and soft support vector regression algorithms. Based on our analysis, we illustrate that adding more samples may be harmful to the test performance of support vector regression, while it is always beneficial when the parameters are optimally selected. Such a result reminds a similar phenomenon observed in modern learning architectures according to which optimally tuned architectures present a decreasing test performance curve with respect to the number of samples.

In this paper, we consider the problem of recovering a binary phase shift keying (BPSK) modulated signal in a massive multiple-input-multiple-output (MIMU) system. The recovery process is done using the box-relaxation method, in which the discrete set {±I}nis relaxed to the convex set [-I,+I]nand solved by a convex optimization program followed by hard thresholding. We assume that the system has a Gaussian channel matrix with one sided left correlation. The entries of the noise vector are assumed to be independent and identically distributed (iid) zero-mean Gaussian. In this work, we precisely characterize the mean squared error (MSE) and the bit error rate (BER) of the box-relaxation decoder in the asymptotic regime where both dimensions grow simultaneously large at a fixed ratio. Numerical simulations validate the theoretical expressions derived in this paper.

Linear discriminant analysis (LDA) is a popular classifier that is built on the assumption of common population covariance matrix across classes. The performance of LDA depends heavily on the quality of estimating the mean vectors and the population covariance matrix. This issue becomes more challenging in high-dimensional settings where the number of features is of the same order as the number of training samples. Several techniques for estimating the covariance matrix can be found in the literature. One of the most popular approaches are estimators based on using a regularized sample covariance matrix, giving the name regularized LDA (R-LDA) to the corresponding classifier. These estimators are known to be more resilient to the sample noise than the traditional sample covariance matrix estimator. However, the main challenge of the regularization approach is the choice of the optimal regularization parameter, as an arbitrary choice could lead to severe degradation of the classifier performance. In this work, we propose an improved LDA classifier based on the assumption that the covariance matrix follows a spiked covariance model. The main principle of our proposed technique is the design of a parametrized inverse covariance matrix estimator, the parameters of which are shown to be easily optimized. Numerical simulations, using both real and synthetic data, show that the proposed classifier yields better classification performance than the classical R-LDA while requiring lower computational complexity.

In this paper, we propose a new regularized robust estimation approach based on the robust τ -estimator applied to linear ill-posed problems in the presence of noise outliers. Additionally, we introduce a new approach to obtain the optimal regularization parameter for the proposed robust estimator by using tools from random matrix theory. Simulation results demonstrate that the proposed approach with its automated regularization parameter selection outperforms a set of benchmark methods.

Visible light communication (VLC) is recognized as a promising technology to complement existing wireless communication systems due to its main advantages such as ease of deployment, low cost and large unlicensed bandwidth. This paper considers the precoding design for a multi-user multiple-input-single-output VLC system. Two major concerns need to be considered while solving such a problem. The first one is related to the inter-user interference, basically inherent to our consideration of a multi-user system, while the second results from the users' mobility, causing imperfect channel estimates. To address both concerns, we propose robust precoding designs that solve both max-min SINR and minimal illumination level problems. The first problem allows users' rates maximization while ensuring fairness and the second problem decides the feasibility of a certain set of target SINRs. The proposed robust designs are studied under different conditions, and are shown to achieve a high gain over their nonrobust counterparts.

Visible light communication (VLC) is an emerging technique that uses light-emitting diodes (LED) to combine communication and illumination. It is considered as a promising scheme for indoor wireless communication that can be deployed at reduced costs while offering high data rate performance. In this paper, we focus on the design of the downlink of a multi-user VLC system. Inherent to multi-user systems is the interference caused by the broadcast nature of the medium. Linear precoding based schemes are among the most popular solutions that have recently been proposed to mitigate inter-user interference. This paper focuses on the design of the optimal linear precoding scheme that solves the max-min signal-to-interference-plus-noise ratio (SINR) problem. The performance of the proposed precoding scheme is studied under different working conditions and compared with the classical zero-forcing precoding. Simulations have been provided to illustrate the high gain of the proposed scheme.

This work focuses on the downlink of a single-cell large-scale MIMO system in which the base station equipped with M antennas serves K single-antenna users. In particular, we are interested in reducing the implementation complexity of the optimal linear precoder (OLP) that minimizes the total power consumption while ensuring target user rates. As most precoding schemes, a major difficulty towards the implementation of OLP is that it requires fast inversions of large matrices at every new channel realizations. To overcome this issue, we aim at designing a linear precoding scheme providing the same performance of OLP but with lower complexity. This is achieved by applying the truncated polynomial expansion (TPE) concept on a per-user basis. To get a further leap in complexity reduction and allow for closed-form expressions of the per-user weighting coefficients, we resort to the asymptotic regime in which M and K grow large with a bounded ratio. Numerical results are used to show that the proposed TPE precoding scheme achieves the same performance of OLP with a significantly lower implementation complexity.