143 citations · 290 across the 47 of their papers we have counts for
53 papers
Dynamic Regret in Online Convex Optimization with Indicator Switching Costs
Naram Mhaisen, George Iosifidis
We study dynamic regret in online convex optimization with an \emph{indicator switching cost}: a fixed penalty incurred whenever two consecutive decisions differ. This captures sta…
Constrained Online Convex Optimization with Memory and Predictions
Mohammed Abdullah, George Iosifidis, Salah Eddine Elayoubi +1
We study Constrained Online Convex Optimization with Memory (COCO-M), where both the loss and the constraints depend on a finite window of past decisions made by the learner. This…
Equitable Multi-Task Learning for AI-RANs
Panayiotis Raptis, Fatih Aslan, George Iosifidis
AI-enabled Radio Access Networks (AI-RANs) are expected to serve heterogeneous users with time-varying learning tasks over shared edge resources. Ensuring equitable inference perfo…
Partially Lazy Gradient Descent for Smoothed Online Learning
Naram Mhaisen, George Iosifidis
We introduce \textsc{-lazyGD}, an online learning algorithm that bridges the gap between greedy Online Gradient Descent (OGD, for ) and lazy GD/dual-averaging (for $k{=}T…
Meta-Learning-Based Handover Management in NextG O-RAN
Michail Kalntis, George Iosifidis, José Suárez-Varela +2
While traditional handovers (THOs) have served as a backbone for mobile connectivity, they increasingly suffer from failures and delays, especially in dense deployments and high-fr…
CHOMET: Conditional Handovers via Meta-Learning
Michail Kalntis, Fernando A. Kuipers, George Iosifidis
Handovers (HOs) are the cornerstone of modern cellular networks for enabling seamless connectivity to a vast and diverse number of mobile users. However, as mobile networks become…
Speed-Aware Network Design: A Parametric Optimization Approach
Ugo Rosolia, Marc Bataillou Almagro, George Iosifidis +2
Network design problems have been studied from the 1950s, as they can be used in a wide range of real-world applications, e.g., design of communication and transportation networks.…
On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning
Naram Mhaisen, George Iosifidis
We revisit the Follow the Regularized Leader (FTRL) framework for Online Convex Optimization (OCO) over compact sets, focusing on achieving dynamic regret guarantees. Prior work ha…
Optimistic Learning for Communication Networks
George Iosifidis, Naram Mhaisen, Douglas J. Leith
AI/ML-based tools are at the forefront of resource management solutions for communication networks. Deep learning, in particular, is highly effective in facilitating fast and high-…
Smooth Handovers via Smoothed Online Learning
Michail Kalntis, Andra Lutu, Jesús Omaña Iglesias +2
With users demanding seamless connectivity, handovers (HOs) have become a fundamental element of cellular networks. However, optimizing HOs is a challenging problem, further exacer…
Optimistic Online Non-stochastic Control via FTRL
Naram Mhaisen, George Iosifidis
This paper brings the concept of ``optimism" to the new and promising framework of online Non-stochastic Control (NSC). Namely, we study how NSC can benefit from a prediction oracl…
Fair Resource Allocation in Virtualized O-RAN Platforms
Fatih Aslan, George Iosifidis, Jose A. Ayala-Romero +2
O-RAN systems and their deployment in virtualized general-purpose computing platforms (O-Cloud) constitute a paradigm shift expected to bring unprecedented performance gains. Howev…
Workflow Optimization for Parallel Split Learning
Joana Tirana, Dimitra Tsigkari, George Iosifidis +1
Split learning (SL) has been recently proposed as a way to enable resource-constrained devices to train multi-parameter neural networks (NNs) and participate in federated learning…
Last Truck Scheduling for Middle-mile Next-day Delivery Coverage
Konstantinos Benidis, Georgios Paschos, Martin Gross +1
We consider an e-commerce retailer operating a supply chain that consists of middle- and last-mile transportation, and study its ability to deliver products stored in warehouses wi…
Adaptive Online Non-stochastic Control
Naram Mhaisen, George Iosifidis
We tackle the problem of Non-stochastic Control (NSC) with the aim of obtaining algorithms whose policy regret is proportional to the difficulty of the controlled environment. Name…
Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning
Michail Kalntis, George Iosifidis, Fernando A. Kuipers
Open Radio Access Network systems, with their virtualized base stations (vBSs), offer operators the benefits of increased flexibility, reduced costs, vendor diversity, and interope…
Reservation of Virtualized Resources with Optimistic Online Learning
Jean-Baptiste Monteil, George Iosifidis, Ivana Dusparic
The virtualization of wireless networks enables new services to access network resources made available by the Network Operator (NO) through a Network Slicing market. The different…
Solving Recurrent MIPs with Semi-supervised Graph Neural Networks
Konstantinos Benidis, Ugo Rosolia, Syama Rangapuram +2
We propose an ML-based model that automates and expedites the solution of MIPs by predicting the values of variables. Our approach is motivated by the observation that many problem…
Bandit Convex Optimisation Revisited: FTRL Achieves Regret
David Young, Douglas Leith, George Iosifidis
We show that a kernel estimator using multiple function evaluations can be easily converted into a sampling-based bandit estimator with expectation equal to the original kernel est…
Quid pro Quo in Streaming Services: Algorithms for Cooperative Recommendations
Dimitra Tsigkari, George Iosifidis, Thrasyvoulos Spyropoulos
Recommendations are employed by Content Providers (CPs) of streaming services in order to boost user engagement and their revenues. Recent works suggest that nudging recommendation…
Energy-aware Scheduling of Virtualized Base Stations in O-RAN with Online Learning
Michail Kalntis, George Iosifidis
The design of Open Radio Access Network (O-RAN) compliant systems for configuring the virtualized Base Stations (vBSs) is of paramount importance for network operators. This task i…
Enabling Long-term Fairness in Dynamic Resource Allocation
T. Si-Salem, G. Iosifidis, G. Neglia
We study the fairness of dynamic resource allocation problem under the -fairness criterion. We recognize two different fairness objectives that naturally arise in this problem:…
Deep Reinforcement Learning for Orchestrating Cost-Aware Reconfigurations of vRANs
Fahri Wisnu Murti, Samad Ali, George Iosifidis +1
Virtualized Radio Access Networks (vRANs) are fully configurable and can be implemented at a low cost over commodity platforms to enable network management flexibility. In this pap…
Learning-Based Orchestration for Dynamic Functional Split and Resource Allocation in vRANs
Fahri Wisnu Murti, Samad Ali, George Iosifidis +1
One of the key benefits of virtualized radio access networks (vRANs) is network management flexibility. However, this versatility raises previously-unseen network management challe…