Search Results for author:
Found 22 papers, 4 papers with code
SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks
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)
Sparse Training for Federated Learning with Regularized Error Correction
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.
A Masked Pruning Approach for Dimensionality Reduction in Communication-Efficient Federated Learning Systems
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).
Deep Multi-Agent Reinforcement Learning for Decentralized Active Hypothesis Testing
These different actions result in observations drawn from various distributions, each associated with a specific hypothesis.
A Genetic Algorithm-Based Approach to Power Allocation in Rate-Splitting Multiple Access Systems
We consider the problem of power allocation in Rate-Splitting Multiple Access (RSMA) systems, where messages are split into common and private messages.
Federated Learning from Heterogeneous Data via Controlled Bayesian Air Aggregation
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.
Multi-Flow Transmission in Wireless Interference Networks: A Convergent Graph Learning Approach
The objective is to develop a multi-flow transmission strategy that routes flows across the wireless interference network to maximize the network utility.
Client Selection for Generalization in Accelerated Federated Learning: A Multi-Armed Bandit Approach
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.
A Communication-Efficient Adaptive Algorithm for Federated Learning under Cumulative Regret
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.
Restless Multi-Armed Bandits under Exogenous Global Markov Process
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.
Learning in Restless Bandits under Exogenous Global Markov Process
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.
Deep Reinforcement Learning for Simultaneous Sensing and Channel Access in Cognitive Networks
Since observations are partial, then both channel sensing and access actions affect the throughput.
Accelerated Gradient Descent Learning over Multiple Access Fading Channels
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).
Federated Learning: A Signal Processing Perspective
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.
Distributed Learning over Markovian Fading Channels for Stable Spectrum Access
By contrast, we consider a more general and practical model, where each channel yields a different expected rate for each user.
Over-the-Air Federated Learning from Heterogeneous Data
Our analysis reveals the ability of COTAF to achieve a convergence rate similar to that achievable over error-free channels.
PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning
However, existing algorithms suffer from a significant performance reduction in the DRL domain.
On Analog Gradient Descent Learning over Multiple Access Fading Channels
The objective function is a sum of the nodes' local loss functions.
Learning in Restless Multi-Armed Bandits via Adaptive Arm Sequencing Rules
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.
Deep Reinforcement One-Shot Learning for Artificially Intelligent Classification Systems
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.
Deep Multi-User Reinforcement Learning for Distributed Dynamic Spectrum Access
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
On Projected Stochastic Gradient Descent Algorithm with Weighted Averaging for Least Squares Regression
The problem of least squares regression of a $d$-dimensional unknown parameter is considered.
