no code implementations • 25 Apr 2024 • Xiaojing Yan, Saeed Razavikia, Carlo Fischione
In this paper, we consider the ChannelComp framework, which facilitates the computation of desired functions by multiple transmitters over a common receiver using digital modulations across a multiple access channel.
no code implementations • 7 Nov 2023 • Saeed Razavikia, José Mairton Barros Da Silva Júnior, Carlo Fischione
Indeed, we propose a new federated edge learning framework in which edge devices use digital modulation for over-the-air uplink transmission to the edge server while they have no access to the channel state information.
no code implementations • 10 Oct 2023 • Saeed Razavikia, José Mairton Barros Da Silva Júnior, Carlo Fischione
However, when we use digital modulations for AirComp, a general belief is that the superposition property of the radio waves returns a meaningless overlapping of the digital signals.
1 code implementation • 27 Sep 2023 • Henrik Hellström, Saeed Razavikia, Viktoria Fodor, Carlo Fischione
The fundamental idea of OAC is to exploit signal superposition to compute functions of multiple simultaneously transmitted signals.
1 code implementation • 27 Aug 2023 • Oscar Stenhammar, Gabor Fodor, Carlo Fischione
The performance of modern wireless communications systems depends critically on the quality of the available channel state information (CSI) at the transmitter and receiver.
no code implementations • 21 Jun 2023 • Sajad Daei, Saeed Razavikia, Marios Kountouris, Mikael Skoglund, Gabor Fodor, Carlo Fischione
Resource allocation and multiple access schemes are instrumental for the success of communication networks, which facilitate seamless wireless connectivity among a growing population of uncoordinated and non-synchronized users.
no code implementations • 1 Mar 2023 • Saeed Razavikia, Jose Mairton Barros da Silva Jr, Carlo Fischione
Over-the-air computation (AirComp) is a known technique in which wireless devices transmit values by analog amplitude modulation so that a function of these values is computed over the communication channel at a common receiver.
no code implementations • 8 Nov 2022 • Shashi Kant, José Mairton B. da Silva Jr., Gabor Fodor, Bo Göransson, Mats Bengtsson, Carlo Fischione
We propose FedTOP-ADMM, which generalizes FedADMM and is based on a three-operator ADMM-type technique that exploits a smooth cost function on the edge server to learn a global model parallel to the edge devices.
no code implementations • 31 Oct 2022 • Afsaneh Mahmoudi, José Mairton Barros Da Silva Júnior, Hossein S. Ghadikolaei, Carlo Fischione
This paper proposes Adaptive Lazily Aggregated Quantized Gradient (A-LAQ), which is a method that significantly extends LAQ by assigning an adaptive number of communication bits during the FL iterations.
no code implementations • 31 Oct 2022 • Saeed Razavikia, Jaume Anguera Peris, Jose Mairton B. da Silva Jr, Carlo Fischione
Federated Edge Learning (FEEL) is a distributed machine learning technique where each device contributes to training a global inference model by independently performing local computations with their data.
no code implementations • 25 May 2022 • Shashi Kant, Mats Bengtsson, Gabor Fodor, Bo Göransson, Carlo Fischione
Although signal distortion-based peak-to-average power ratio (PAPR) reduction is a feasible candidate for orthogonal frequency division multiplexing (OFDM) to meet standard/regulatory requirements, the error vector magnitude (EVM) stemming from the PAPR reduction has a deleterious impact on the performance of high data-rate achieving multiple-input multiple-output (MIMO) systems.
no code implementations • 16 Apr 2022 • Afsaneh Mahmoudi, Hossein S. Ghadikolaei, José Mairton Barros Da Silva Júnior, Carlo Fischione
We propose an iteration-termination method that trade-offs the training performance and networking costs.
no code implementations • 19 Nov 2021 • Henrik Hellström, Viktoria Fodor, Carlo Fischione
Finally, we propose a heuristic for selecting the optimal number of retransmissions, which can be calculated before training the ML model.
no code implementations • 27 May 2021 • Pangun Park, Piergiuseppe Di Marco, Carlo Fischione
Numerical results show that our proposed over-the-air controller achieves a huge widening of the stability region in terms of sampling time and delay, and a significant reduction of the computation error of the control signal.
no code implementations • 26 Apr 2021 • José Mairton B. da Silva Jr., Konstantinos Ntougias, Ioannis Krikidis, Gábor Fodor, Carlo Fischione
We investigate the trade-off between the number of communication rounds and communication round time while harvesting energy to compensate the energy expenditure.
no code implementations • 1 Jan 2021 • Hossein S. Ghadikolaei, Thomas Ohlson Timoudas, Carlo Fischione
We show that our approach can substantially outperform vanilla SVRG and its variants in terms of both convergence rate and total cost of running the algorithm.
no code implementations • 7 Dec 2020 • Yeongwoo Kim, Ezeddin Al Hakim, Johan Haraldson, Henrik Eriksson, José Mairton B. da Silva Jr., Carlo Fischione
To overcome these limitations, in this paper, we propose a three-phased data clustering algorithm, namely: generative adversarial network-based clustering, cluster calibration, and cluster division.
no code implementations • 25 Sep 2020 • Shashi Kant, Mats Bengtsson, Gabor Fodor, Bo Göransson, Carlo Fischione
In this paper we propose a novel spectral precoding approach which constrains the EVM while complying with the mask requirements.
no code implementations • 31 Aug 2020 • Henrik Hellström, José Mairton B. da Silva Jr, Mohammad Mohammadi Amiri, Mingzhe Chen, Viktoria Fodor, H. Vincent Poor, Carlo Fischione
As data generation increasingly takes place on devices without a wired connection, machine learning (ML) related traffic will be ubiquitous in wireless networks.
no code implementations • 23 Mar 2020 • Rong Du, Sindri Magnússon, Carlo Fischione
To ensure communication efficiency, this article proposes to model the measurement compression at IoT nodes and the inference at the base station or cloud as a deep neural network (DNN).
no code implementations • 19 Mar 2020 • Hossein S. Ghadikolaei, Hadi Ghauch, Gabor Fodor, Mikael Skoglund, Carlo Fischione
Inter-operator spectrum sharing in millimeter-wave bands has the potential of substantially increasing the spectrum utilization and providing a larger bandwidth to individual user equipment at the expense of increasing inter-operator interference.
no code implementations • 16 Dec 2019 • Michele Cucuzzella, Thijs Bouman, Krishna Chaitanya Kosaraju, Geertje Schuitema, N. H. Lemmen, Steph Johnson-Zawadzki, Carlo Fischione, Linda Steg, Jacquelien M. A. Scherpen
In this paper, a novel distributed control strategy addressing a (feasible) psycho-social-physical welfare problem in islanded Direct Current (DC) smart grids is proposed.
no code implementations • ICML 2018 • Othmane Mazhar, Cristian R. Rojas, Carlo Fischione, Mohammad R. Hesamzadeh
We address the new problem of estimating a piece-wise constant signal with the purpose of detecting its change points and the levels of clusters.
no code implementations • 6 Jun 2018 • Hadi Ghauch, Mikael Skoglund, Hossein Shokri-Ghadikolaei, Carlo Fischione, Ali H. Sayed
We summarize our recent findings, where we proposed a framework for learning a Kolmogorov model, for a collection of binary random variables.
BIG-bench Machine Learning Interpretable Machine Learning +1
no code implementations • 23 May 2018 • Hadi Ghauch, Hossein Shokri-Ghadikolaei, Carlo Fischione, Mikael Skoglund
The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting.