12 accepted papers
Deep equilibrium (DEQ) models are widely recognized as a memory efficient alternative to standard neural networks, achieving state-of-the-art performance in language modeling and computer vision tasks. These models solve a fixed point equation instead of explicitly computing the output, which sets t…
In this paper, we propose deep-unfolded versions of the recently proposed superiorized adaptive projected subgradient method for MIMO detection. The proposed methods require a single matrix inverse for initialization, and they have a quadratic per-iteration complexity. Extensive simulations with rea…
We propose a truly decentralized algorithm for solving distributed convex optimization problems with possibly time-varying objectives and dynamic networks. It is especially suitable for solving convex feasibility problems with possibly infinitely many sets, and its main novelty is that it covers pra…
In this paper, we propose a set-theoretic framework for MIMO detection. Various low-complexity MIMO detection algorithms achieve excellent performance on i.i.d. Gaussian channels, but they typically incur high performance loss if realistic channel models are considered. Compared to existing low-comp…
We propose a deep learning-based method that uses spatial and temporal information extracted from the sub-6GHz band to predict/track beams in the millimeter-wave (mmWave) band. In more detail, we consider a dual-band communication system operating in both the sub-6GHz and mmWave bands. The objective…
We propose a novel algorithm to estimate the channel covariance matrix of a desired user in multiuser massive MIMO systems. The algorithm uses only knowledge of the array response and rough knowledge of the angular support of the incoming signals, which are assumed to be separated in a well-defined…
Hybrid analog-/digital beamforming architectures are a promising means of reducing power consumption and hardware costs in large multi-antenna transceivers. However, channel estimation becomes more complicated compared with conventional (fully-digital) architectures because multiple measurements (pi…
Semidefinite relaxation followed by randomization is a well-known approach for approximating a solution to the NP-hard max-min fair multicast beamforming problem. While providing a good approximation to the optimal solution, this approach commonly involves the use of computationally demanding interi…
We propose novel approaches to identify the existence of fixed points of the so-called weakly standard interference mappings, which include the well-known standard and general interference mappings as particular cases. The approaches are based on the concept of spectral radius of asymptotic mappings…
We propose a hybrid dictionary approach for distributed kernel-based adaptive learning of a nonlinear function by a network of nodes. The hybrid dictionary incorporates a local part to improve learning of high frequency components in the function within the local domain of each node and a global par…
We propose a learning algorithm for cell-load approximation in wireless networks. The proposed algorithm is robust in the sense that it is designed to cope with the uncertainty arising from a small number of training samples. This scenario is highly relevant in wireless networks where training has t…
We propose a novel power control algorithm for the minimization of the peak load in the widely used load coupled network model, which is an abstract model able to capture the behavior of current and possibly future wireless networks. We first prove that the solution to the optimization problem we po…