Kobi Cohen
YOU?
Author Swipe
View article: Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach Open
Federated learning (FL) is an emerging machine learning (ML) paradigm used to train models across multiple nodes (i.e., clients) holding local data sets, without explicitly exchanging the data. It has attracted a growing interest in recent…
View article: Asymptotically Optimal Search for a Change Point Anomaly under a Composite Hypothesis Model
Asymptotically Optimal Search for a Change Point Anomaly under a Composite Hypothesis Model Open
We address the problem of searching for a change point in an anomalous process among a finite set of M processes. Specifically, we address a composite hypothesis model in which each process generates measurements following a common distrib…
View article: A Stable Polygamy Approach to Spectrum Access with Channel Reuse
A Stable Polygamy Approach to Spectrum Access with Channel Reuse Open
We introduce a new and broader formulation of the stable marriage problem (SMP), called the stable polygamy problem (SPP), where multiple individuals from a larger group $L$ of $|L|$ individuals can be matched with a single individual from…
View article: RRO: A Regularized Routing Optimization Algorithm for Enhanced Throughput and Low Latency with Efficient Complexity
RRO: A Regularized Routing Optimization Algorithm for Enhanced Throughput and Low Latency with Efficient Complexity Open
In the rapidly evolving landscape of wireless networks, achieving enhanced throughput with low latency for data transmission is crucial for future communication systems. While low complexity OSPF-type solutions have shown effectiveness in …
View article: SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks
SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks Open
We consider the problem of dynamic channel allocation (DCA) in cognitive communication networks with the goal of maximizing a global signal-to-interference-plus-noise ratio (SINR) measure under a specified target quality of service (QoS)-S…
View article: Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing
Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing Open
We consider a decentralized formulation of the active hypothesis testing (AHT) problem, where multiple agents gather noisy observations from the environment with the purpose of identifying the correct hypothesis. At each time step, agents …
View article: Sparse Training for Federated Learning with Regularized Error Correction
Sparse Training for Federated Learning with Regularized Error Correction Open
Federated Learning (FL) has attracted much interest due to the significant advantages it brings to training deep neural network (DNN) models. However, since communications and computation resources are limited, training DNN models in FL sy…
View article: A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems
A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems Open
Federated Learning (FL) represents a growing machine learning (ML) paradigm designed for training models across numerous nodes that retain local datasets, all without directly exchanging the underlying private data with the parameter serve…
View article: Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing
Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing Open
We consider a decentralized formulation of the active hypothesis testing (AHT) problem, where multiple agents gather noisy observations from the environment with the purpose of identifying the correct hypothesis. At each time step, agents …
View article: A Genetic Algorithm-Based Approach to Power Allocation in Rate-Splitting Multiple Access Systems
A Genetic Algorithm-Based Approach to Power Allocation in Rate-Splitting Multiple Access Systems Open
We consider the problem of power allocation in Rate-Splitting Multiple Access (RSMA) systems, where messages are split into common and private messages. The common and private streams are jointly transmitted to allow efficient use of the b…
View article: Federated Learning from Heterogeneous Data via Controlled Bayesian Air Aggregation
Federated Learning from Heterogeneous Data via Controlled Bayesian Air Aggregation Open
Federated learning (FL) is an emerging machine learning paradigm for training models across multiple edge devices holding local data sets, without explicitly exchanging the data. Recently, over-the-air (OTA) FL has been suggested to reduce…
View article: Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach
Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach Open
We consider the problem of of multi-flow transmission in wireless networks, where data signals from different flows can interfere with each other due to mutual interference between links along their routes, resulting in reduced link capaci…
View article: Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach Open
Federated learning (FL) is an emerging machine learning (ML) paradigm used to train models across multiple nodes (i.e., clients) holding local data sets, without explicitly exchanging the data. It has attracted a growing interest in recent…
View article: A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret
A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret Open
We consider the problem of online stochastic optimization in a distributed setting with $M$ clients connected through a central server. We develop a distributed online learning algorithm that achieves order-optimal cumulative regret with l…
View article: Subgradient Descent Learning Over Fading Multiple Access Channels With Over-the-Air Computation
Subgradient Descent Learning Over Fading Multiple Access Channels With Over-the-Air Computation Open
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 the computation based on data received from the nodes, which …
View article: An Online Learning Approach to Shortest Path and Backpressure Routing in Wireless Networks
An Online Learning Approach to Shortest Path and Backpressure Routing in Wireless Networks Open
We consider the problem of adaptive routing in wireless communication networks. The problem is investigated in the online learning context, where the link states are assumed to be random variables drawn from unknown distributions, independ…
View article: Federated Learning: A signal processing perspective
Federated Learning: A signal processing perspective Open
The dramatic success of deep learning is largely due to the availability of\ndata. Data samples are often acquired on edge devices, such as smart phones,\nvehicles and sensors, and in some cases cannot be shared due to privacy\nconsiderati…
View article: Table of Contents [Table of Contents]
Table of Contents [Table of Contents] Open
View article: An Online Learning Approach to Shortest Path and Backpressure Routing in Wireless Networks
An Online Learning Approach to Shortest Path and Backpressure Routing in Wireless Networks Open
We consider the adaptive routing problem in multihop wireless networks. The link states are assumed to be random variables drawn from unknown distributions, independent and identically distributed across links and time. This model has attr…
View article: Restless Multi-Armed Bandits under Exogenous Global Markov Process
Restless Multi-Armed Bandits under Exogenous Global Markov Process Open
We consider an extension to the restless multi-armed bandit (RMAB) problem with unknown arm dynamics, where an unknown exogenous global Markov process governs the rewards distribution of each arm. Under each global state, the rewards proce…
View article: Anomaly Search over Composite Hypotheses in Hierarchical Statistical Models
Anomaly Search over Composite Hypotheses in Hierarchical Statistical Models Open
Detection of anomalies among a large number of processes is a fundamental task that has been studied in multiple research areas, with diverse applications spanning from spectrum access to cyber-security. Anomalous events are characterized …
View article: Distributed Learning Over Markovian Fading Channels for Stable Spectrum Access
Distributed Learning Over Markovian Fading Channels for Stable Spectrum Access Open
We consider the problem of multi-user spectrum access in wireless networks. The bandwidth is divided into orthogonal channels, and users aim to access the spectrum. Each user chooses a single channel for transmission at each time slot. T…
View article: Anomaly Search With Multiple Plays Under Delay and Switching Costs
Anomaly Search With Multiple Plays Under Delay and Switching Costs Open
The problem of searching for $L$ anomalous processes among $M$ processes is\nconsidered. At each time, the decision maker can observe a subset of $K$\nprocesses (i.e., multiple plays). The measurement drawn when observing a\nprocess follow…
View article: Learning in Restless Bandits under Exogenous Global Markov Process
Learning in Restless Bandits under Exogenous Global Markov Process Open
We consider an extension to the restless multi-armed bandit (RMAB) problem with unknown arm dynamics, where an unknown exogenous global Markov process governs the rewards distribution of each arm. Under each global state, the rewards proce…
View article: Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networks
Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networks Open
We consider the problem of dynamic spectrum access (DSA) in cognitive wireless networks, where only partial observations are available to the users due to narrowband sensing and transmissions. The cognitive network consists of primary user…
View article: Accelerated Gradient Descent Learning Over Multiple Access Fading Channels
Accelerated Gradient Descent Learning Over Multiple Access Fading Channels Open
We consider a distributed learning problem in a wireless network, consisting of N distributed edge devices and a parameter server (PS). The objective function is a sum of the edge devices' local loss functions, who aim to train a shared mo…
View article: Accelerated Gradient Descent Learning over Multiple Access Fading\n Channels
Accelerated Gradient Descent Learning over Multiple Access Fading\n Channels Open
We consider a distributed learning problem in a wireless network, consisting\nof N distributed edge devices and a parameter server (PS). The objective\nfunction is a sum of the edge devices' local loss functions, who aim to train a\nshared…
View article: Traitement automatique de la langue pour une réponse rapide dans le cadre d’une maladie émergente : exemple de la COVID-19
Traitement automatique de la langue pour une réponse rapide dans le cadre d’une maladie émergente : exemple de la COVID-19 Open
View article: Controlled Testing and Isolation for Suppressing Covid-19
Controlled Testing and Isolation for Suppressing Covid-19 Open
The Corona virus disease 2019 (COVID-19) has significantly affected lives of people around the world. Today, isolation policy is mostly enforced by identifying infected individuals based on symptoms when these appear or by testing people a…
View article: Suppressing the impact of the COVID-19 pandemic using controlled testing and isolation
Suppressing the impact of the COVID-19 pandemic using controlled testing and isolation Open