Related papers: Optimal Training Design for Over-the-Air Polynomia…

We consider the task of estimating a low-rank matrix from non-linear and noisy observations. We prove a strong universality result showing that Bayes-optimal performances are characterized by an equivalent Gaussian model with an effective…

Peak to average power ratio (PAPR) constrained power allocation in single carrier multiuser (MU) single-input multiple-output (SIMO) systems with iterative frequency domain (FD) soft cancelation (SC) minimum mean squared error (MMSE)…

Federated learning (FL) has been considered a promising privacy preserving distributed edge learning framework. Over-the-air computation (AirComp) leveraging analog transmission enables the aggregation of local updates directly over-the-air…

Although multiple works have proposed energy-efficient resource allocation schemes for Massive Multiple-Input Multiple-Output (M-MIMO) system, most approaches overlook the potential of optimizing Power Amplifier (PA) transmission power…

This paper considers over-the-air federated learning (OTA-FL). OTA-FL exploits the superposition property of the wireless medium, and performs model aggregation over the air for free. Thus, it can greatly reduce the communication cost…

Recent studies indicate that the noise characteristics of phasor measurement units (PMUs) can be more accurately described by non-Gaussian distributions. Consequently, estimation techniques based on Gaussian noise assumptions may produce…

For the problem of high-dimensional sparse linear regression, it is known that an $\ell_0$-based estimator can achieve a $1/n$ "fast" rate on the prediction error without any conditions on the design matrix, whereas in absence of…

Stochastic approximation techniques play an important role in solving many problems encountered in machine learning or adaptive signal processing. In these contexts, the statistics of the data are often unknown a priori or their direct…

Many reinforcement learning algorithms rely on value estimation, however, the most widely used algorithms -- namely temporal difference algorithms -- can diverge under both off-policy sampling and nonlinear function approximation. Many…

This paper addresses the suboptimal energy efficiency of conventional digital precoding schemes in multiple-input multiple-output (MIMO) systems. Through an analysis of the power amplifier (PA) output power distribution associated with…

To enable intelligent beam training, a large language model (LLM)-enabled beam training framework is proposed for the pinching antenna system (PASS) in downlink multi-user multiple-input multiple-output (MIMO) communications. A novel…

Optimal Bayesian design techniques provide an estimate for the best parameters of an experiment in order to maximize the value of measurements prior to the actual collection of data. In other words, these techniques explore the space of…

Decentralized state estimation in a communication-constrained sensor network is considered. The exchanged estimates are dimension-reduced to reduce the communication load using a linear mapping to a lower-dimensional space. The mean squared…

Data-dependent superimposed training (DDST) scheme has shown the potential to achieve high bandwidth efficiency, while encounters symbol misidentification caused by hardware imperfection. To tackle these challenges, a joint model and data…

Large-scale multiple-antenna systems have been identified as a promising technology for the next generation of wireless systems. However, by scaling up the number of receive antennas the energy consumption will also increase. One possible…

We consider the problem of signal estimation in a generalized linear model (GLM). GLMs include many canonical problems in statistical estimation, such as linear regression, phase retrieval, and 1-bit compressed sensing. Recent work has…

Overparameterization in deep learning is powerful: Very large models fit the training data perfectly and yet often generalize well. This realization brought back the study of linear models for regression, including ordinary least squares…

We consider machine learning techniques to develop low-latency approximate solutions to a class of inverse problems. More precisely, we use a probabilistic approach for the problem of recovering sparse stochastic signals that are members of…

Quantum communication offers many applications, with teleportation and superdense coding being two of the most fundamental. In these protocols, pre-shared entanglement enables either the faithful transfer of quantum states or the…

This paper investigates whether sequence models can learn to perform numerical algorithms, e.g. gradient descent, on the fundamental problem of least squares. Our goal is to inherit two properties of standard algorithms from numerical…