no code implementations • 17 Feb 2024 • Yaniv Cohen, Tomer Gafni, Ronen Greenberg, Kobi Cohen
We propose a novel multi-agent reinforcement learning (RL) framework for distributed DCA, named Channel Allocation RL To Overlapped Networks (CARLTON).
Multi-agent Reinforcement Learning Reinforcement Learning (RL)
no code implementations • 21 Dec 2023 • Ran Greidi, Kobi Cohen
FLARE presents a novel sparse training approach via accumulated pulling of the updated models with regularization on the embeddings in the FL process, providing a powerful solution to the staleness effect, and pushing sparsity to an exceptional level.
no code implementations • 6 Dec 2023 • Tamir L. S. Gez, Kobi Cohen
In this paper, we develop a novel algorithm that overcomes these limitations by synergistically combining a pruning-based method with the FL process, resulting in low-dimensional representations of the model with minimal communication cost, dubbed Masked Pruning over FL (MPFL).
no code implementations • 14 Sep 2023 • Hadar Szostak, Kobi Cohen
These different actions result in observations drawn from various distributions, each associated with a specific hypothesis.
no code implementations • 8 Sep 2023 • Temitope O. Fajemilehin, Kobi Cohen
We consider the problem of power allocation in Rate-Splitting Multiple Access (RSMA) systems, where messages are split into common and private messages.
no code implementations • 30 Mar 2023 • Tomer Gafni, Kobi Cohen, Yonina C. Eldar
To handle statistical heterogeneity of users data, which is a second major challenge in FL, we extend BAAF to allow for appropriate local updates by the users and develop the Controlled Bayesian Air Aggregation Federated-learning (COBAAF) algorithm.
no code implementations • 27 Mar 2023 • Raz Paul, Kobi Cohen, Gil Kedar
The objective is to develop a multi-flow transmission strategy that routes flows across the wireless interference network to maximize the network utility.
no code implementations • 18 Mar 2023 • Dan Ben Ami, Kobi Cohen, Qing Zhao
In FL, selected clients train their local models and send a function of the models to the server, which consumes a random processing and transmission time.
no code implementations • 21 Jan 2023 • Sudeep Salgia, Qing Zhao, Tamir Gabay, Kobi Cohen
We develop a distributed online learning algorithm that achieves order-optimal cumulative regret with low communication cost measured in the total number of bits transmitted over the entire learning horizon.
no code implementations • 28 Feb 2022 • Tomer Gafni, Michal Yemini, Kobi Cohen
Motivated by recent studies on related RMAB settings, the regret is defined as the reward loss with respect to a player that knows the dynamics of the problem, and plays at each time t the arm that maximizes the expected immediate value.
no code implementations • 17 Dec 2021 • Tomer Gafni, Michal Yemini, Kobi Cohen
Motivated by recent studies on related RMAB settings, the regret is defined as the reward loss with respect to a player that knows the dynamics of the problem, and plays at each time $t$ the arm that maximizes the expected immediate value.
no code implementations • 24 Oct 2021 • Yoel Bokobza, Ron Dabora, Kobi Cohen
Since observations are partial, then both channel sensing and access actions affect the throughput.
no code implementations • 26 Jul 2021 • Raz Paul, Yuval Friedman, Kobi Cohen
The objective function is a sum of the edge devices' local loss functions, who aim to train a shared model by communicating with the PS over multiple access channels (MAC).
no code implementations • 31 Mar 2021 • Tomer Gafni, Nir Shlezinger, Kobi Cohen, Yonina C. Eldar, H. Vincent Poor
Learning in a federated manner differs from conventional centralized machine learning, and poses several core unique challenges and requirements, which are closely related to classical problems studied in the areas of signal processing and communications.
no code implementations • 27 Jan 2021 • Tomer Gafni, Kobi Cohen
By contrast, we consider a more general and practical model, where each channel yields a different expected rate for each user.
1 code implementation • 27 Sep 2020 • Tomer Sery, Nir Shlezinger, Kobi Cohen, Yonina C. Eldar
Our analysis reveals the ability of COTAF to achieve a convergence rate similar to that achievable over error-free channels.
1 code implementation • 14 Jan 2020 • Dor Livne, Kobi Cohen
However, existing algorithms suffer from a significant performance reduction in the DRL domain.
1 code implementation • 20 Aug 2019 • Tomer Sery, Kobi Cohen
The objective function is a sum of the nodes' local loss functions.
no code implementations • 19 Jun 2019 • Tomer Gafni, Kobi Cohen
Although existing methods have shown a logarithmic regret order with time in this RMAB setting, the theoretical analysis shows a significant improvement in the regret scaling with respect to the system parameters under ASR.
2 code implementations • 4 Aug 2018 • Anton Puzanov, Kobi Cohen
Second, we develop the first open-source software for practical artificially intelligent one-shot classification systems with limited resources for the benefit of researchers in related fields.
no code implementations • 9 Apr 2017 • Oshri Naparstek, Kobi Cohen
In the beginning of each time slot, each user selects a channel and transmits a packet with a certain transmission probability.
Networking and Internet Architecture
no code implementations • 9 Jun 2016 • Kobi Cohen, Angelia Nedic, R. Srikant
The problem of least squares regression of a $d$-dimensional unknown parameter is considered.