no code implementations • 26 Mar 2024 • Khac-Hoang Ngo, Johan Östman, Giuseppe Durisi, Alexandre Graell i Amat
In this paper, we delve into the privacy implications of SecAgg by treating it as a local differential privacy (LDP) mechanism for each local update.
no code implementations • 29 Feb 2024 • Javad Aliakbari, Johan Östman, Alexandre Graell i Amat
We address the challenge of federated learning on graph-structured data distributed across multiple clients.
no code implementations • 26 Feb 2024 • Yibo Wu, Ulf Gustavsson, Mikko Valkama, Alexandre Graell i Amat, Henk Wymeersch
The use of up to hundreds of antennas in massive multi-user (MU) multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) poses a complexity challenge for digital predistortion (DPD) aiming to linearize the nonlinear power amplifiers (PAs).
no code implementations • 26 Dec 2023 • Jinxiang Song, Vincent Lauinger, Christian Häger, Jochen Schröder, Alexandre Graell i Amat, Laurent Schmalen, Henk Wymeersch
We propose a novel frequency-domain blind equalization scheme for coherent optical communications.
no code implementations • 21 May 2023 • Yibo Wu, Luca Sanguinetti, Ulf Gustavsson, Alexandre Graell i Amat, Henk Wymeersch
Cell-Free massive MIMO networks provide huge power gains and resolve inter-cell interference by coherent processing over a massive number of distributed instead of co-located antennas in access points (APs).
no code implementations • 9 May 2023 • Marvin Xhemrishi, Johan Östman, Antonia Wachter-Zeh, Alexandre Graell i Amat
Inspired by group testing, the framework leverages overlapping groups of clients to identify the presence of malicious clients in the groups via a decoding operation.
no code implementations • 22 Feb 2023 • Jinxiang Song, Vincent Lauinger, Yibo Wu, Christian Häger, Jochen Schröder, Alexandre Graell i Amat, Laurent Schmalen, Henk Wymeersch
Furthermore, we show that for the linear channel, the proposed scheme exhibits better convergence properties than the \ac{MMSE}-based, the \ac{CMA}-based, and the \ac{VAE}-based equalizers in terms of both convergence speed and robustness to variations in training batch size and learning rate.
no code implementations • 28 Jan 2023 • Vukan Ninkovic, Dejan Vukobratovic, Christian Häger, Henk Wymeersch, Alexandre Graell i Amat
Most of today's communication systems are designed to target reliable message recovery after receiving the entire encoded message (codeword).
no code implementations • 10 May 2022 • Yibo Wu, Ulf Gustavsson, Mikko Valkama, Alexandre Graell i Amat, Henk Wymeersch
In this paper, we propose a convolutional neural network (CNN)-based DPD in the frequency domain, taking place before the precoding, where the dimensionality of the signal space depends on the number of users, instead of the number of BS antennas.
no code implementations • 16 Dec 2021 • Reent Schlegel, Siddhartha Kumar, Eirik Rosnes, Alexandre Graell i Amat
For a scenario with 120 devices, CodedPaddedFL achieves a speed-up factor of 18 for an accuracy of 95% on the MNIST dataset compared to conventional FL.
1 code implementation • 29 Nov 2021 • Jinxiang Song, Christian Häger, Jochen Schröder, Alexandre Graell i Amat, Henk Wymeersch
Simulation results show that the reinforcement-learning-based algorithm achieves similar performance to the standard supervised end-to-end learning approach assuming perfect channel knowledge.
no code implementations • 23 Nov 2021 • Yibo Wu, Jinxiang Song, Christian Häger, Ulf Gustavsson, Alexandre Graell i Amat, Henk Wymeersch
We propose an over-the-air digital predistortion optimization algorithm using reinforcement learning.
no code implementations • 30 Sep 2021 • Siddhartha Kumar, Reent Schlegel, Eirik Rosnes, Alexandre Graell i Amat
The proposed scheme combines one-time padding to preserve privacy and gradient codes to yield resiliency against stragglers and consists of two phases.
no code implementations • 9 Jun 2021 • Jinxiang Song, Zonglong He, Christian Häger, Magnus Karlsson, Alexandre Graell i Amat, Henk Wymeersch, Jochen Schröder
We demonstrate, for the first time, experimental over-the-fiber training of transmitter neural networks (NNs) using reinforcement learning.
no code implementations • 6 Apr 2021 • Yibo Wu, Ulf Gustavsson, Alexandre Graell i Amat, Henk Wymeersch
Neural networks (NNs) for multiple hardware impairments mitigation of a realistic direct conversion transmitter are impractical due to high computational complexity.
no code implementations • 29 Mar 2021 • Jinxiang Song, Christian Häger, Jochen Schröder, Alexandre Graell i Amat, Henk Wymeersch
We propose an end-to-end learning-based approach for superchannel systems impaired by non-ideal hardware component.
no code implementations • 24 Dec 2020 • Min Qiu, Xiaowei Wu, Alexandre Graell i Amat, Jinhong Yuan
In this paper, we study a class of spatially coupled turbo codes, namely partially information- and partially parity-coupled turbo codes.
Information Theory Signal Processing Information Theory
no code implementations • 12 May 2020 • Yibo Wu, Ulf Gustavsson, Alexandre Graell i Amat, Henk Wymeersch
Tracking the nonlinear behavior of an RF power amplifier (PA) is challenging.
no code implementations • 21 Jan 2020 • Andreas Buchberger, Christian Häger, Henry D. Pfister, Laurent Schmalen, Alexandre Graell i Amat
In this paper, we introduce a method to tailor an overcomplete parity-check matrix to (neural) BP decoding using machine learning.
no code implementations • 8 Oct 2018 • Albin Severinson, Alexandre Graell i Amat, Eirik Rosnes, Francisco Lazaro, Gianluigi Liva
We propose a coded distributed computing scheme based on Raptor codes to address the straggler problem.
no code implementations • 21 Dec 2017 • Albin Severinson, Alexandre Graell i Amat, Eirik Rosnes
We propose two coded schemes for the distributed computing problem of multiplying a matrix by a set of vectors.