Searcharxiv⌕ Search

arXiv subjects

Kobi Cohen

Publications and source records attributed to Kobi Cohen.

At least 37 records · Page 2Linked to original sources
arXiv2023

Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach

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 capacities. The objective is to develop a multi-flow transmission strategy that routes flows across the wireless interference network to maximize the network utility. However, obtaining an optimal solution is computationally expensive due to the large state and action spaces involved. To tackle this challenge, we introduce a novel algorithm called Dual-stage Interference-Aware Multi-flow Optimization of Network Data-signals (DIAMOND). The design of DIAMOND allows for a hybrid centralized-distributed implementation, which is a characteristic of 5G and beyond technologies with centralized unit deployments. A centralized stage computes the multi-flow transmission strategy using a novel design of graph neural network (GNN) reinforcement learning (RL) routing agent. Then, a distributed stage improves the performance based on a novel design of distributed learning updates. We provide a theoretical analysis of DIAMOND and prove that it converges to the optimal multi-flow transmission strategy as time increases. We also present extensive simulation results over various network topologies (random deployment, NSFNET, GEANT2), demonstrating the superior performance of DIAMOND compared to existing methods.

cs.LG↗
arXiv2023

A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret

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 low communication cost measured in the total number of bits transmitted over the entire learning horizon. This is in contrast to existing studies which focus on the offline measure of simple regret for learning efficiency. The holistic measure for communication cost also departs from the prevailing approach that \emph{separately} tackles the communication frequency and the number of bits in each communication round.

cs.LG↗
arXiv2023

Federated Learning from Heterogeneous Data via Controlled Bayesian Air Aggregation

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 the bandwidth and energy consumption, by allowing the users to transmit their data simultaneously over a Multiple Access Channel (MAC). However, this approach results in channel noise directly affecting the optimization procedure, which may degrade the accuracy of the trained model. In this paper we jointly exploit the prior distribution of local weights and the channel distribution, and develop an OTA FL algorithm based on a Bayesian approach for signal aggregation. Our proposed algorithm, dubbed Bayesian Air Aggregation Federated learning (BAAF), is shown to effectively mitigate noise and fading effects induced by the channel. 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. In addition to using a Bayesian approach to average the channel output, COBAAF controls the drift in local updates using a judicious design of correction terms. We analyze the convergence of the learned global model using BAAF and COBAAF in noisy and heterogeneous environment, showing their ability to achieve a convergence rate similar to that achieved over error-free channels. Simulation results demonstrate the improved convergence of BAAF and COBAAF over existing algorithms in machine learning tasks.

eess.SP↗
arXiv2023

Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach

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 years due to its advantages in terms of privacy considerations, and communication resources. 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. The server updates the global model and broadcasts it back to the clients. The client selection problem in FL is to schedule a subset of the clients for training and transmission at each given time so as to optimize the learning performance. In this paper, we present a novel multi-armed bandit (MAB)-based approach for client selection to minimize the training latency without harming the ability of the model to generalize, that is, to provide reliable predictions for new observations. We develop a novel algorithm to achieve this goal, dubbed Bandit Scheduling for FL (BSFL). We analyze BSFL theoretically, and show that it achieves a logarithmic regret, defined as the loss of BSFL as compared to a genie that has complete knowledge about the latency means of all clients. Furthermore, simulation results using synthetic and real datasets demonstrate that BSFL is superior to existing methods.

cs.LG↗
arXiv2022

Restless Multi-Armed Bandits under Exogenous Global Markov Process

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 process of each arm evolves according to an unknown Markovian rule, which is non-identical among different arms. At each time, a player chooses an arm out of N arms to play, and receives a random reward from a finite set of reward states. The arms are restless, that is, their local state evolves regardless of the player's actions. 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. The objective is to develop an arm-selection policy that minimizes the regret. To that end, we develop the Learning under Exogenous Markov Process (LEMP) algorithm. We analyze LEMP theoretically and establish a finite-sample bound on the regret. We show that LEMP achieves a logarithmic regret order with time. We further analyze LEMP numerically and present simulation results that support the theoretical findings and demonstrate that LEMP significantly outperforms alternative algorithms.

cs.LG↗
arXiv2022

Anomaly Search over Composite Hypotheses in Hierarchical Statistical Models

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 by deviations in data distributions, and thus can be inferred from noisy observations based on statistical methods. In some scenarios, one can often obtain noisy observations aggregated from a chosen subset of processes. Such hierarchical search can further minimize the sample complexity while retaining accuracy. An anomaly search strategy should thus be designed based on multiple requirements, such as maximizing the detection accuracy; efficiency, be efficient in terms of sample complexity; and be able to cope with statistical models that are known only up to some missing parameters (i.e., composite hypotheses). In this paper, we consider anomaly detection with observations taken from a chosen subset of processes that conforms to a predetermined tree structure with partially known statistical model. We propose Hierarchical Dynamic Search (HDS), a sequential search strategy that uses two variations of the Generalized Log Likelihood Ratio (GLLR) statistic, and can be used for detection of multiple anomalies. HDS is shown to be order-optimal in terms of the size of the search space, and asymptotically optimal in terms of detection accuracy. An explicit upper bound on the error probability is established for the finite sample regime. In addition to extensive experiments on synthetic datasets, experiments have been conducted on the DARPA intrusion detection dataset, showing that HDS is superior to existing methods.

cs.IT↗
arXiv2022

An Online Learning Approach to Shortest Path and Backpressure Routing in Wireless Networks

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 attracted a growing interest recently in cognitive radio networks and adaptive communication systems. In such networks, devices are cognitive in the sense of learning the link states and updating the transmission parameters to allow efficient resource utilization. This model contrasts sharply with the vast literature on routing algorithms that assumed complete knowledge about the link state means. The goal is to design an algorithm that learns online optimal paths for data transmissions to maximize the network throughput while attaining low path cost over flows in the network. We develop a novel Online Learning for Shortest path and Backpressure (OLSB) algorithm to achieve this goal. We analyze the performance of OLSB rigorously and show that it achieves a logarithmic regret with time, defined as the loss of an algorithm as compared to a genie that has complete knowledge about the link state means. We further evaluate the performance of OLSB numerically via extensive simulations, which support the theoretical findings and demonstrate its high efficiency.

cs.NI↗
arXiv2022

Learning in Restless Bandits under Exogenous Global Markov Process

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 process of each arm evolves according to an unknown Markovian rule, which is non-identical among different arms. At each time, a player chooses an arm out of $N$ arms to play, and receives a random reward from a finite set of reward states. The arms are restless, that is, their local state evolves regardless of the player's actions. 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. The objective is to develop an arm-selection policy that minimizes the regret. To that end, we develop the Learning under Exogenous Markov Process (LEMP) algorithm. We analyze LEMP theoretically and establish a finite-sample bound on the regret. We show that LEMP achieves a logarithmic regret order with time. We further analyze LEMP numerically and present simulation results that support the theoretical findings and demonstrate that LEMP significantly outperforms alternative algorithms.

cs.LG↗
arXiv2021

Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networks

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 users (PUs) and a secondary user (SU), which operate in a time duplexing regime. The traffic pattern for each PU is assumed to be unknown to the SU and is modeled as a finite-memory Markov chain. Since observations are partial, then both channel sensing and access actions affect the throughput. The objective is to maximize the SU's long-term throughput. To achieve this goal, we develop a novel algorithm that learns both access and sensing policies via deep Q-learning, dubbed Double Deep Q-network for Sensing and Access (DDQSA). To the best of our knowledge, this is the first paper that solves both sensing and access policies for DSA via deep Q-learning. Second, we analyze the optimal policy theoretically to validate the performance of DDQSA. Although the general DSA problem is P-SPACE hard, we derive the optimal policy explicitly for a common model of a cyclic user dynamics. Our results show that DDQSA learns a policy that implements both sensing and channel access, and significantly outperforms existing approaches.

cs.IT↗
arXiv2021

Accelerated Gradient Descent Learning over Multiple Access Fading Channels

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 model by communicating with the PS over multiple access channels (MAC). This problem has attracted a growing interest in distributed sensing systems, and more recently in federated learning, known as over-the-air computation. In this paper, we develop a novel Accelerated Gradient-descent Multiple Access (AGMA) algorithm that uses momentum-based gradient signals over noisy fading MAC to improve the convergence rate as compared to existing methods. Furthermore, AGMA does not require power control or beamforming to cancel the fading effect, which simplifies the implementation complexity. We analyze AGMA theoretically, and establish a finite-sample bound of the error for both convex and strongly convex loss functions with Lipschitz gradient. For the strongly convex case, we show that AGMA approaches the best-known linear convergence rate as the network increases. For the convex case, we show that AGMA significantly improves the sub-linear convergence rate as compared to existing methods. Finally, we present simulation results using real datasets that demonstrate better performance by AGMA.

cs.LG↗
arXiv2021

Federated Learning: A Signal Processing Perspective

The dramatic success of deep learning is largely due to the availability of data. Data samples are often acquired on edge devices, such as smart phones, vehicles and sensors, and in some cases cannot be shared due to privacy considerations. Federated learning is an emerging machine learning paradigm for training models across multiple edge devices holding local datasets, without explicitly exchanging the data. 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. Consequently, dedicated schemes derived from these areas are expected to play an important role in the success of federated learning and the transition of deep learning from the domain of centralized servers to mobile edge devices. In this article, we provide a unified systematic framework for federated learning in a manner that encapsulates and highlights the main challenges that are natural to treat using signal processing tools. We present a formulation for the federated learning paradigm from a signal processing perspective, and survey a set of candidate approaches for tackling its unique challenges. We further provide guidelines for the design and adaptation of signal processing and communication methods to facilitate federated learning at large scale.

eess.SP↗
arXiv2021

Anomaly Search with Multiple Plays under Delay and Switching Costs

The problem of searching for $L$ anomalous processes among $M$ processes is considered. At each time, the decision maker can observe a subset of $K$ processes (i.e., multiple plays). The measurement drawn when observing a process follows one of two different distributions, depending on whether the process is normal or abnormal. The goal is to design a policy that minimizes the Bayes risk which balances between the sample complexity, detection errors, and the switching cost associated with switching across processes. We develop a policy, dubbed consecutive controlled sensing (CCS), to achieve this goal. On the one hand, by contrast to existing studies on controlled sensing, the CCS policy senses processes consecutively to reduce the switching cost. On the other hand, the policy controls the sensing operation in a closed-loop manner to switch between processes when necessary to guarantee reliable inference. We prove theoretically that CCS is asymptotically optimal in terms of minimizing the Bayes risk as the detection error approaches zero (i.e., the sample complexity increases). Simulation results demonstrate strong performance of CCS in the finite regime as well.

cs.IT↗
arXiv2021

Distributed Learning over Markovian Fading Channels for Stable Spectrum Access

We consider the problem of multi-user spectrum access in wireless networks. The bandwidth is divided into K orthogonal channels, and M users aim to access the spectrum. Each user chooses a single channel for transmission at each time slot. The state of each channel is modeled by a restless unknown Markovian process. Previous studies have analyzed a special case of this setting, in which each channel yields the same expected rate for all users. By contrast, we consider a more general and practical model, where each channel yields a different expected rate for each user. This model adds a significant challenge of how to efficiently learn a channel allocation in a distributed manner to yield a global system-wide objective. We adopt the stable matching utility as the system objective, which is known to yield strong performance in multichannel wireless networks, and develop a novel Distributed Stable Strategy Learning (DSSL) algorithm to achieve the objective. We prove theoretically that DSSL converges to the stable matching allocation, and the regret, defined as the loss in total rate with respect to the stable matching solution, has a logarithmic order with time. Finally, simulation results demonstrate the strong performance of the DSSL algorithm.

eess.SP↗
arXiv2020

Over-the-Air Federated Learning from Heterogeneous Data

Federated learning (FL) is a framework for distributed learning of centralized models. In FL, a set of edge devices train a model using their local data, while repeatedly exchanging their trained updates with a central server. This procedure allows tuning a centralized model in a distributed fashion without having the users share their possibly private data. In this paper, we focus on over-the-air (OTA) FL, which has been suggested recently to reduce the communication overhead of FL due to the repeated transmissions of the model updates by a large number of users over the wireless channel. In OTA FL, all users simultaneously transmit their updates as analog signals over a multiple access channel, and the server receives a superposition of the analog transmitted signals. However, this approach results in the channel noise directly affecting the optimization procedure, which may degrade the accuracy of the trained model. We develop a Convergent OTA FL (COTAF) algorithm which enhances the common local stochastic gradient descent (SGD) FL algorithm, introducing precoding at the users and scaling at the server, which gradually mitigates the effect of the noise. We analyze the convergence of COTAF to the loss minimizing model and quantify the effect of a statistically heterogeneous setup, i.e. when the training data of each user obeys a different distribution. Our analysis reveals the ability of COTAF to achieve a convergence rate similar to that achievable over error-free channels. Our simulations demonstrate the improved convergence of COTAF over vanilla OTA local SGD for training using non-synthetic datasets. Furthermore, we numerically show that the precoding induced by COTAF notably improves the convergence rate and the accuracy of models trained via OTA FL.

cs.LG↗
arXiv2020

PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning

The recent success of deep neural networks (DNNs) for function approximation in reinforcement learning has triggered the development of Deep Reinforcement Learning (DRL) algorithms in various fields, such as robotics, computer games, natural language processing, computer vision, sensing systems, and wireless networking. Unfortunately, DNNs suffer from high computational cost and memory consumption, which limits the use of DRL algorithms in systems with limited hardware resources. In recent years, pruning algorithms have demonstrated considerable success in reducing the redundancy of DNNs in classification tasks. However, existing algorithms suffer from a significant performance reduction in the DRL domain. In this paper, we develop the first effective solution to the performance reduction problem of pruning in the DRL domain, and establish a working algorithm, named Policy Pruning and Shrinking (PoPS), to train DRL models with strong performance while achieving a compact representation of the DNN. The framework is based on a novel iterative policy pruning and shrinking method that leverages the power of transfer learning when training the DRL model. We present an extensive experimental study that demonstrates the strong performance of PoPS using the popular Cartpole, Lunar Lander, Pong, and Pacman environments. Finally, we develop an open source software for the benefit of researchers and developers in related fields.

cs.LG↗
arXiv2019

Searching for Anomalies over Composite Hypotheses

The problem of detecting anomalies in multiple processes is considered. We consider a composite hypothesis case, in which the measurements drawn when observing a process follow a common distribution with an unknown parameter (vector), whose value lies in normal or abnormal parameter spaces, depending on its state. The objective is a sequential search strategy that minimizes the expected detection time subject to an error probability constraint. We develop a deterministic search algorithm with the following desired properties. First, when no additional side information on the process states is known, the proposed algorithm is asymptotically optimal in terms of minimizing the detection delay as the error probability approaches zero. Second, when the parameter value under the null hypothesis is known and equal for all normal processes, the proposed algorithm is asymptotically optimal as well, with better detection time determined by the true null state. Third, when the parameter value under the null hypothesis is unknown, but is known to be equal for all normal processes, the proposed algorithm is consistent in terms of achieving error probability that decays to zero with the detection delay. Finally, an explicit upper bound on the error probability under the proposed algorithm is established for the finite sample regime. Extensive experiments on synthetic dataset and DARPA intrusion detection dataset are conducted, demonstrating strong performance of the proposed algorithm over existing methods.

cs.IT↗
arXiv2019

On Analog Gradient Descent Learning over Multiple Access Fading Channels

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 received data from a large number of distributed nodes which transmit over a noisy fading MAC. The objective function is a sum of the nodes' local loss functions. This problem has attracted a growing interest in distributed sensing systems, and more recently in federated learning. We develop a novel Gradient-Based Multiple Access (GBMA) algorithm to solve the distributed learning problem over MAC. Specifically, the nodes transmit an analog function of the local gradient using common shaping waveforms and the network edge receives a superposition of the analog transmitted signals used for updating the estimate. GBMA does not require power control or beamforming to cancel the fading effect as in other algorithms, and operates directly with noisy distorted gradients. We analyze the performance of GBMA theoretically, and prove that it can approach the convergence rate of the centralized gradient descent (GD) algorithm in large networks. Specifically, we establish a finite-sample bound of the error for both convex and strongly convex loss functions with Lipschitz gradient. Furthermore, we provide energy scaling laws for approaching the centralized convergence rate as the number of nodes increases. Finally, experimental results support the theoretical findings, and demonstrate strong performance of GBMA using synthetic and real data.

cs.LG↗
arXiv2019

Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rules

We consider a class of restless multi-armed bandit (RMAB) problems with unknown arm dynamics. At each time, a player chooses an arm out of N arms to play, referred to as an active arm, and receives a random reward from a finite set of reward states. The reward state of the active arm transits according to an unknown Markovian dynamics. The reward state of passive arms (which are not chosen to play at time t) evolves according to an arbitrary unknown random process. The objective is an arm-selection policy that minimizes the regret, defined as the reward loss with respect to a player that always plays the most rewarding arm. This class of RMAB problems has been studied recently in the context of communication networks and financial investment applications. We develop a strategy that selects arms to be played in a consecutive manner, dubbed Adaptive Sequencing Rules (ASR) algorithm. The sequencing rules for selecting arms under the ASR algorithm are adaptively updated and controlled by the current sample reward means. By designing judiciously the adaptive sequencing rules, we show that the ASR algorithm achieves a logarithmic regret order with time, and a finite-sample bound on the regret is established. 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. Extensive simulation results support the theoretical study and demonstrate strong performance of the algorithm as compared to existing methods.

cs.LG↗