Subgradient descent learning with over-the-air computation
TLS Gez, K Cohen - ICASSP 2023-2023 IEEE International …, 2023 - ieeexplore.ieee.org
We consider a distributed learning problem in a communication network, consisting of N
distributed nodes and a central parameter server (PS). The computation is made by the PS …
distributed nodes and a central parameter server (PS). The computation is made by the PS …
Subgradient descent learning over fading multiple access channels with over-the-air computation
TLS Gez, K Cohen - IEEE Access, 2023 - ieeexplore.ieee.org
We focus on a distributed learning problem in a communication network, consisting of
distributed nodes and a central parameter server (PS). The PS is responsible for performing …
distributed nodes and a central parameter server (PS). The PS is responsible for performing …
Accelerated gradient descent learning over multiple access fading channels
R Paul, Y Friedman, K Cohen - IEEE Journal on Selected Areas …, 2021 - ieeexplore.ieee.org
We consider a distributed learning problem in a wireless network, consisting of distributed
edge devices and a parameter server (PS). The objective function is a sum of the edge …
edge devices and a parameter server (PS). The objective function is a sum of the edge …
On analog gradient descent learning over multiple access fading channels
T Sery, K Cohen - IEEE Transactions on Signal Processing, 2020 - ieeexplore.ieee.org
We consider a distributed learning problem over multiple access channel (MAC) using a
large wireless network. The computation is made by the network edge and is based on …
large wireless network. The computation is made by the network edge and is based on …
A sequential gradient-based multiple access for distributed learning over fading channels
T Sery, K Cohen - 2019 57th Annual Allerton Conference on …, 2019 - ieeexplore.ieee.org
A distributed learning problem over multiple access channel (MAC) using a large wireless
network is considered. The objective function is a sum of the nodes' local loss functions. The …
network is considered. The objective function is a sum of the nodes' local loss functions. The …
On analog distributed approximate Newton with determinantal averaging
This paper considers the problem of communication and computation-efficient distributed
learning via a wireless fading Multiple Access Channel (MAC). The distributed learning task …
learning via a wireless fading Multiple Access Channel (MAC). The distributed learning task …
Federated learning with partial gradients over-the-air
W Wang, Z Chen, N Pappas… - 2023 20th Annual IEEE …, 2023 - ieeexplore.ieee.org
We develop a theoretical framework to study the training of federated learning models with
partial gradients via over-the-air computing. The system consists of an edge server and …
partial gradients via over-the-air computing. The system consists of an edge server and …
Optimal number of edge devices in distributed learning over wireless channels
J Song, M Kountouris - 2020 IEEE 21st International Workshop …, 2020 - ieeexplore.ieee.org
We consider a distributed learning system, where a parameter server (PS) assigns data and
computational tasks to edge devices to build a global model. Distributing data to multiple …
computational tasks to edge devices to build a global model. Distributing data to multiple …
Cost-efficient distributed optimization in machine learning over wireless networks
A Mahmoudi, HS Ghadikolaei… - ICC 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
This paper addresses the problem of distributed training of a machine learning model over
the nodes of a wireless communication network. Existing distributed training methods are …
the nodes of a wireless communication network. Existing distributed training methods are …
On in-network learning. A comparative study with federated and split learning
M Moldoveanu, A Zaidi - 2021 IEEE 22nd International …, 2021 - ieeexplore.ieee.org
In this paper, we consider a problem in which distributively extracted features are used for
performing inference in wireless networks. We elaborate on our proposed architecture …
performing inference in wireless networks. We elaborate on our proposed architecture …