no code implementations • 28 Feb 2023 • Rajarshi Saha, Mohamed Seif, Michal Yemini, Andrea J. Goldsmith, H. Vincent Poor
This work considers the problem of Distributed Mean Estimation (DME) over networks with intermittent connectivity, where the goal is to learn a global statistic over the data samples localized across distributed nodes with the help of a central server.
no code implementations • 23 May 2022 • Michal Yemini, Rajarshi Saha, Emre Ozfatura, Deniz Gündüz, Andrea J. Goldsmith
We present a semi-decentralized federated learning algorithm wherein clients collaborate by relaying their neighbors' local updates to a central parameter server (PS).
no code implementations • 24 Feb 2022 • Michal Yemini, Rajarshi Saha, Emre Ozfatura, Deniz Gündüz, Andrea J. Goldsmith
Intermittent connectivity of clients to the parameter server (PS) is a major bottleneck in federated edge learning frameworks.
no code implementations • 23 Feb 2022 • Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith
We derive an information-theoretic lower bound for the minimax risk under this setting and propose a matching upper bound using randomized embedding-based algorithms which is tight up to constant factors.
no code implementations • 3 Oct 2021 • Michal Yemini, Stephanie Gil, Andrea J. Goldsmith
The connectivity of each sensor cluster is intermittent and depends on the available communication opportunities of the sensors to the fusion center.
1 code implementation • 13 Mar 2021 • Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith
As a consequence, quantizing these embeddings followed by an inverse transform to the original space yields a source coding method with optimal covering efficiency while utilizing just $R$-bits per dimension.
no code implementations • 12 Jan 2021 • Nir Shlezinger, Nariman Farsad, Yonina C. Eldar, Andrea J. Goldsmith
We present an introduction to model-based machine learning for communication systems.
no code implementations • 30 Oct 2020 • Michal Yemini, Elza Erkip, Andrea J. Goldsmith
Our numerical results show that our scheme decreases the number of users in the system whose rate falls below the guaranteed rate, set to $128$kbps, $256$kbps or $512$kbps, when compared with our previously proposed optimization methods.
no code implementations • 5 Jun 2020 • Nir Shlezinger, Nariman Farsad, Yonina C. Eldar, Andrea J. Goldsmith
Learned factor graph can be realized using compact neural networks that are trainable using small training sets, or alternatively, be used to improve upon existing deep inference systems.
no code implementations • 14 Feb 2020 • Nariman Farsad, Nir Shlezinger, Andrea J. Goldsmith, Yonina C. Eldar
The design of symbol detectors in digital communication systems has traditionally relied on statistical channel models that describe the relation between the transmitted symbols and the observed signal at the receiver.
no code implementations • 31 Jan 2020 • Nir Shlezinger, Nariman Farsad, Yonina C. Eldar, Andrea J. Goldsmith
In particular, we propose to use machine learning (ML) tools to learn the factor graph, instead of the overall system task, which in turn is used for inference by message passing over the learned graph.
no code implementations • 25 Jul 2019 • Yun Liao, Nariman Farsad, Nir Shlezinger, Yonina C. Eldar, Andrea J. Goldsmith
This paper proposes to use a deep neural network (DNN)-based symbol detector for mmWave systems such that CSI acquisition can be bypassed.
1 code implementation • 26 May 2019 • Nir Shlezinger, Nariman Farsad, Yonina C. Eldar, Andrea J. Goldsmith
Our numerical evaluations demonstrate that the performance of ViterbiNet, which is ignorant of the CSI, approaches that of the CSI-based Viterbi algorithm, and is capable of tracking time-varying channels without needing instantaneous CSI or additional training data.
no code implementations • 6 Apr 2015 • Yuxin Chen, Changho Suh, Andrea J. Goldsmith
In particular, our results isolate a family of \emph{minimum} \emph{channel divergence measures} to characterize the degree of measurement corruption, which together with the size of the minimum cut of $\mathcal{G}$ dictates the feasibility of exact information recovery.