no code implementations • 19 Jul 2022 • Ozan Aygün, Mohammad Kazemi, Deniz Gündüz, Tolga M. Duman
Our scheme utilizes OTA cluster aggregations for the communication of the MUs with their corresponding IS, and OTA global aggregations from the ISs to the PS.
no code implementations • 21 Dec 2021 • Ozan Aygün, Mohammad Kazemi, Deniz Gündüz, Tolga M. Duman
Federated learning (FL) over wireless communication channels, specifically, over-the-air (OTA) model aggregation framework is considered.
1 code implementation • 18 Oct 2021 • Eduin E. Hernandez, Stefano Rini, Tolga M. Duman
In order to correct for the inherent bias in this approximation, the algorithm retains in memory an accumulation of the outer products that are not used in the approximation.
no code implementations • 24 Sep 2021 • Mert Kalfa, Mehmetcan Gok, Arda Atalik, Busra Tegin, Tolga M. Duman, Orhan Arikan
The proposed semantic signal processing framework can easily be tailored for specific applications and goals in a diverse range of signal processing applications.
1 code implementation • 4 Mar 2021 • Busra Tegin, Eduin. E. Hernandez, Stefano Rini, Tolga M. Duman
Large-scale machine learning and data mining methods routinely distribute computations across multiple agents to parallelize processing.
Image Classification Distributed, Parallel, and Cluster Computing Information Theory Information Theory
no code implementations • 19 Oct 2020 • Mohammad Mohammadi Amiri, Tolga M. Duman, Deniz Gunduz, Sanjeev R. Kulkarni, H. Vincent Poor
At each iteration, wireless devices perform local updates using their local data and the most recent global model received from the PS, and send their local updates to the PS over a wireless fading multiple access channel (MAC).
no code implementations • 1 Oct 2020 • Busra Tegin, Tolga M. Duman
We study collaborative machine learning systems where a massive dataset is distributed across independent workers which compute their local gradient estimates based on their own datasets.
no code implementations • 8 Jul 2019 • Mohammad Mohammadi Amiri, Tolga M. Duman, Deniz Gunduz
At each iteration of the DSGD algorithm wireless devices compute gradient estimates with their local datasets, and send them to the PS over a wireless fading multiple access channel (MAC).
1 code implementation • 12 Nov 2012 • Mojtaba Rahmati, Tolga M. Duman
We then provide an upper bound on the concatenated deletion channel capacity $C(d)$ in terms of the weighted average of $C(d_1)$, $C(d_2)$ and the parameters of the three channels.
Information Theory Information Theory