Related papers: Towards efficient feature sharing in MIMO architec…

To meet the unprecedented mobile traffic demands of future wireless networks, a paradigm shift from conventional cellular networks to distributed communication systems is imperative. Cell-free massive multiple-input multiple-output…

Large-scale multiple-input multiple-output (MIMO) holds great promise for the fifth-generation (5G) and future communication systems. In near-field scenarios, the spherical wavefront model is commonly utilized to accurately depict the…

The high spectral efficiency of massive MIMO (Multiple Input Multiple Output) is mainly achieved through the exploitation of spatial multiplexing, i.e. by using a high number of MIMO layers that are applied simultaneously to many users. The…

Cell-free massive MIMO (multiple-input multiple-output) is a promising network architecture for beyond 5G systems, which can particularly offer more uniform data rates across the coverage area. Recent works have shown how reconfigurable…

Superior performance and ease of implementation have fostered the adoption of Convolutional Neural Networks (CNNs) for a wide array of inference and reconstruction tasks. CNNs implement three basic blocks: convolution, pooling and pointwise…

We consider multi-input multi-output (MIMO) communications over multi-mode fibers (MMFs). Current MMF standards, such as OM3 and OM4, use fibers with core radii of 50 \mu m, allowing hundreds of modes to propagate. Unfortunately, due to…

We investigate the minimal number of failures that can partition a system where processes communicate both through shared memory and by message passing. We prove that this number precisely captures the resilience that can be achieved by…

One of the distinguishing characteristics of modern deep learning systems is that they typically employ neural network architectures that utilize enormous numbers of parameters, often in the millions and sometimes even in the billions.…

Beamforming techniques are proposed for a joint multi-input-multi-output (MIMO) radar-communication (RadCom) system, where a single device acts both as a radar and a communication base station (BS) by simultaneously communicating with…

Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on…

Companies are using machine learning to solve real-world problems and are developing hundreds to thousands of features in the process. They are building feature engineering pipelines as part of MLOps life cycle to transform data from…

With the growing interest in cell-free massive multiple-input multiple-output (MIMO) systems, the benefits of single-antenna access points (APs) versus multi-antenna APs must be analyzed in order to optimize deployment. In this paper, we…

Multi-agent reinforcement learning has emerged as a powerful framework for enabling agents to learn complex, coordinated behaviors but faces persistent challenges regarding its generalization, scalability and sample efficiency. Recent…

Increasing number of filters in deeper layers when feature maps are decreased is a widely adopted pattern in convolutional network design. It can be found in classical CNN architectures and in automatic discovered models. Even CNS methods…

In this work, we explore the limitations of combining models by averaging intermediate features, referred to as model merging, and propose a new direction for achieving collective model intelligence through what we call compatible…

Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of…

The cost of radio frequency (RF) chains is the biggest drawback of massive MIMO millimeter wave networks. By employing spatial modulation (SM), it is possible to implement lower number of RF chains than transmit antennas but still achieve…

The beamforming techniques have been recently studied as possible enablers for underlay spectrum sharing. The existing beamforming techniques have several common limitations: they are usually system model specific, cannot operate with…

In this paper, we present our spectrum sharing algorithm between a multi-input multi-output (MIMO) radar and Long Term Evolution (LTE) cellular system with multiple base stations (BS)s. We analyze the performance of MIMO radars in detecting…

Multi-task learning holds the promise of less data, parameters, and time than training of separate models. We propose a method to automatically search over multi-task architectures while taking resource constraints into consideration. We…