arXiv subjects

George Iosifidis

Publications and source records attributed to George Iosifidis.

At least 19 recordsLinked to original sources

arXiv2026

Partially Lazy Gradient Descent for Smoothed Online Learning

We introduce \textsc{$k$-lazyGD}, an online learning algorithm that bridges the gap between greedy Online Gradient Descent (OGD, for $k{=}1$) and lazy GD/dual-averaging (for $k{=}T$), creating a spectrum between reactive and stable updates. We analyze this spectrum in Smoothed Online Convex Optimization (SOCO), where the learner incurs both hitting and movement costs. Our main contribution is establishing that laziness is possible without sacrificing hitting performance: we prove that \textsc{$k$-lazyGD} achieves the optimal dynamic regret $\mathcal{O}(\sqrt{(P_T{+}1)T})$ for any laziness slack $k$ up to $Θ(\sqrt{T/P_T})$, where $P_T$ is the comparator path length. This result formally connects the allowable laziness to the comparator's shifts, showing that \textsc{$k$-lazyGD} can retain the inherently small movements of lazy methods without compromising tracking ability. We base our analysis on the Follow the Regularized Leader (FTRL) framework, and derive a matching lower bound. Since the slack depends on $P_T$, an ensemble of learners with various slacks is used, yielding a method that is provably stable when it can be, and agile when it must be.

cs.LG↗

arXiv2026

Constrained Online Convex Optimization with Memory and Predictions

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 setting extends the previously studied unconstrained online optimization with memory framework and captures practical problems such as the control of constrained dynamical systems and scheduling with reconfiguration budgets. For this problem, we propose the first algorithms that achieve sublinear regret and sublinear cumulative constraint violation under time-varying constraints, both with and without predictions of future loss and constraint functions. Without predictions, we introduce an adaptive penalty approach that guarantees sublinear regret and constraint violation. When short-horizon and potentially unreliable predictions are available, we reinterpret the problem as online learning with delayed feedback and design an optimistic algorithm whose performance improves as prediction accuracy improves, while remaining robust when predictions are inaccurate. Our results bridge the gap between classical constrained online convex optimization and memory-dependent settings, and provide a versatile learning toolbox with diverse applications.

cs.LG↗

arXiv2026

On the Dynamic Regret of Following the Regularized Leader: Optimism with History Pruning

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 has highlighted the framework's limitations in dynamic environments due to its tendency to produce "lazy" iterates. However, building on insights showing FTRL's ability to produce "agile" iterates, we show that it can indeed recover known dynamic regret bounds through optimistic composition of future costs and careful linearization of past costs, which can lead to pruning some of them. This new analysis of FTRL against dynamic comparators yields a principled way to interpolate between lazy and agile updates and offers several benefits, including refined control over regret terms, optimism without cyclic dependence, and the application of minimal recursive regularization akin to AdaFTRL. More broadly, we show that it is not the "lazy" projection style of FTRL that hinders (optimistic) dynamic regret, but the decoupling of the algorithm's state (linearized history) from its iterates, allowing the state to grow arbitrarily. Instead, pruning synchronizes these two when necessary.

cs.LG↗

arXiv2026

Equitable Multi-Task Learning for AI-RANs

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 performance across these users requires adaptive and fair learning mechanisms. This paper introduces an online-within-online fair multi-task learning (OWO-FMTL) framework that ensures long-term equity across users. The method combines two learning loops: an outer loop updating the shared model across rounds and an inner loop rebalancing user priorities within each round with a lightweight primal-dual update. Equity is quantified via generalized alpha-fairness, allowing a trade-off between efficiency and fairness. The framework guarantees diminishing performance disparity over time and operates with low computational overhead suitable for edge deployment. Experiments on convex and deep learning tasks confirm that OWO-FMTL outperforms existing multi-task learning baselines under dynamic scenarios.

cs.LG↗

arXiv2025

Meta-Learning-Based Handover Management in NextG O-RAN

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-frequency bands. To address these limitations, 3GPP introduced Conditional Handovers (CHOs) that enable proactive cell reservations and user-driven execution. However, both handover (HO) types present intricate trade-offs in signaling, resource usage, and reliability. This paper presents unique, countrywide mobility management datasets from a top-tier mobile network operator (MNO) that offer fresh insights into these issues and call for adaptive and robust HO control in next-generation networks. Motivated by these findings, we propose CONTRA, a framework that, for the first time, jointly optimizes THOs and CHOs within the O-RAN architecture. We study two variants of CONTRA: one where users are a priori assigned to one of the HO types, reflecting distinct service or user-specific requirements, as well as a more dynamic formulation where the controller decides on-the-fly the HO type, based on system conditions and needs. To this end, it relies on a practical meta-learning algorithm that adapts to runtime observations and guarantees performance comparable to an oracle with perfect future information (universal no-regret). CONTRA is specifically designed for near-real-time deployment as an O-RAN xApp and aligns with the 6G goals of flexible and intelligent control. Extensive evaluations leveraging crowdsourced datasets show that CONTRA improves user throughput and reduces both THO and CHO switching costs, outperforming 3GPP-compliant and Reinforcement Learning (RL) baselines in dynamic and real-world scenarios.

cs.NI↗

arXiv2025

CHOMET: Conditional Handovers via Meta-Learning

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 more complex with more diverse users and smaller cells, traditional HOs face significant challenges, such as prolonged delays and increased failures. To mitigate these issues, 3GPP introduced conditional handovers (CHOs), a new type of HO that enables the preparation (i.e., resource allocation) of multiple cells for a single user to increase the chance of HO success and decrease the delays in the procedure. Despite its advantages, CHO introduces new challenges that must be addressed, including efficient resource allocation and managing signaling/communication overhead from frequent cell preparations and releases. This paper presents a novel framework aligned with the O-RAN paradigm that leverages meta-learning for CHO optimization, providing robust dynamic regret guarantees and demonstrating at least 180% superior performance than other 3GPP benchmarks in volatile signal conditions.

cs.LG↗

arXiv2025

Speed-Aware Network Design: A Parametric Optimization Approach

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. In classical network design problems, the objective is to minimize the cost of routing the demand flow through a graph. In this paper, we introduce a generalized version of such a problem, where the objective is to tradeoff routing costs and delivery speed; we introduce the concept of speed-coverage, which is defined as the number of unique items that can be sent to destinations in less than 1-day. Speed-coverage is a function of both the network design and the inventory stored at origin nodes, e.g., an item can be delivered in 1-day if it is in-stock at an origin that can reach a destination within 24 hours. Modeling inventory is inherently complex, since inventory coverage is described by an integer function with a large number of points (exponential to the number of origin sites), each one to be evaluated using historical data. To bypass this complexity, we first leverage a parametric optimization approach, which converts the non-linear joint routing and speed-coverage optimization problem into an equivalent mixed-integer linear program. Then, we propose a sampling strategy to avoid evaluating all the points of the speed-coverage function. The proposed method is evaluated on a series of numerical tests with representative scenarios and network sizes. We show that when considering the routing costs and monetary gains resulting from speed-coverage, our approach outperforms the baseline by 8.36% on average.

math.OC↗

arXiv2025

Last Truck Scheduling for Middle-mile Next-day Delivery Coverage

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 within a day from customer's order time. Successful next-day delivery requires inventory availability and timely truck schedules in the middle-mile and in this paper we assume a fixed inventory position and focus on optimizing the middle-mile last truck schedule. We formulate a novel optimization problem which decides the departure of the last truck at each (potential) network connection in order to maximize the number of customer orders that are served with next-day promise. We show that the respective next-day delivery optimization is a combinatorial problem that is NP-hard to approximate within $(1-1/e)opt\approx 0.632opt$, hence every retailer that offers one-day deliveries has to deal with this complexity barrier. We study three variants of the problem motivated by operational constraints that different retailers encounter, and propose solutions schemes tailored to each problem's properties. To that end, we rely on greedy submodular maximization, pipage rounding techniques, and Lagrangian heuristics. The algorithms are scalable, offer worst-case optimality gap guarantees, and evaluated in realistic datasets and network scenarios were found to achieve even near-optimal results.

cs.DS↗

arXiv2025

Optimistic Learning for Communication Networks

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-performing decision-making whenever representative training data is available to build offline accurate models. Conversely, online learning solutions do not require training and enable adaptive decisions based on runtime observations, alas are often overly conservative. This extensive tutorial proposes the use of optimistic learning (OpL) as a decision engine for resource management frameworks in modern communication systems. When properly designed, such solutions can achieve fast and high-performing decisions -- comparable to offline-trained models -- while preserving the robustness and performance guarantees of the respective online learning approaches. We introduce the fundamental concepts, algorithms and results of OpL, discuss the roots of this theory and present different approaches to defining and achieving optimism. We proceed to showcase how OpL can enhance resource management in communication networks for several key problems such as caching, edge computing, network slicing, and workload assignment in decentralized O-RAN platforms. Finally, we discuss the open challenges that must be addressed to unlock the full potential of this new resource management approach.

cs.NI↗

arXiv2025

Smooth Handovers via Smoothed Online Learning

With users demanding seamless connectivity, handovers (HOs) have become a fundamental element of cellular networks. However, optimizing HOs is a challenging problem, further exacerbated by the growing complexity of mobile networks. This paper presents the first countrywide study of HO optimization, through the prism of Smoothed Online Learning (SOL). We first analyze an extensive dataset from a commercial mobile network operator (MNO) in Europe with more than 40M users, to understand and reveal important features and performance impacts on HOs. Our findings highlight a correlation between HO failures/delays, and the characteristics of radio cells and end-user devices, showcasing the impact of heterogeneity in mobile networks nowadays. We subsequently model UE-cell associations as dynamic decisions and propose a realistic system model for smooth and accurate HOs that extends existing approaches by (i) incorporating device and cell features on HO optimization, and (ii) eliminating (prior) strong assumptions about requiring future signal measurements and knowledge of end-user mobility. Our algorithm, aligned with the O-RAN paradigm, provides robust dynamic regret guarantees, even in challenging environments, and shows superior performance in multiple scenarios with real-world and synthetic data.

cs.NI↗

arXiv2024

Adaptive Resource Allocation for Virtualized Base Stations in O-RAN with Online Learning

Open Radio Access Network systems, with their virtualized base stations (vBSs), offer operators the benefits of increased flexibility, reduced costs, vendor diversity, and interoperability. Optimizing the allocation of resources in a vBS is challenging since it requires knowledge of the environment, (i.e., "external'' information), such as traffic demands and channel quality, which is difficult to acquire precisely over short intervals of a few seconds. To tackle this problem, we propose an online learning algorithm that balances the effective throughput and vBS energy consumption, even under unforeseeable and "challenging'' environments; for instance, non-stationary or adversarial traffic demands. We also develop a meta-learning scheme, which leverages the power of other algorithmic approaches, tailored for more "easy'' environments, and dynamically chooses the best performing one, thus enhancing the overall system's versatility and effectiveness. We prove the proposed solutions achieve sub-linear regret, providing zero average optimality gap even in challenging environments. The performance of the algorithms is evaluated with real-world data and various trace-driven evaluations, indicating savings of up to 64.5% in the power consumption of a vBS compared with state-of-the-art benchmarks.

cs.NI↗

arXiv2024

Through the Telco Lens: A Countrywide Empirical Study of Cellular Handovers

Cellular networks rely on handovers (HOs) as a fundamental element to enable seamless connectivity for mobile users. A comprehensive analysis of HOs can be achieved through data from Mobile Network Operators (MNOs); however, the vast majority of studies employ data from measurement campaigns within confined areas and with limited end-user devices, thereby providing only a partial view of HOs. This paper presents the first countrywide analysis of HO performance, from the perspective of a top-tier MNO in a European country. We collect traffic from approximately 40M users for 4 weeks and study the impact of the radio access technologies (RATs), device types, and manufacturers on HOs across the country. We characterize the geo-temporal dynamics of horizontal (intra-RAT) and vertical (inter-RATs) HOs, at the district level and at millisecond granularity, and leverage open datasets from the country's official census office to associate our findings with the population. We further delve into the frequency, duration, and causes of HO failures, and model them using statistical tools. Our study offers unique insights into mobility management, highlighting the heterogeneity of the network and devices, and their effect on HOs.

cs.NI↗

arXiv2024

Optimistic Online Non-stochastic Control via FTRL

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 oracle of unknown quality responsible for forecasting future costs. The posed problem is first reduced to an optimistic learning with delayed feedback problem, which is handled through the Optimistic Follow the Regularized Leader (OFTRL) algorithmic family. This reduction enables the design of \texttt{OptFTRL-C}, the first Disturbance Action Controller (DAC) with optimistic policy regret bounds. These new bounds are commensurate with the oracle's accuracy, ranging from $\mathcal{O}(1)$ for perfect predictions to the order-optimal $\mathcal{O}(\sqrt{T})$ even when all predictions fail. By addressing the challenge of incorporating untrusted predictions into online control, this work contributes to the advancement of the NSC framework and paves the way toward effective and robust learning-based controllers.

cs.LG↗

arXiv2024

Adaptive Online Non-stochastic Control

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. Namely, we tailor the Follow The Regularized Leader (FTRL) framework to dynamical systems by using regularizers that are proportional to the actual witnessed costs. The main challenge arises from using the proposed adaptive regularizers in the presence of a state, or equivalently, a memory, which couples the effect of the online decisions and requires new tools for bounding the regret. Via new analysis techniques for NSC and FTRL integration, we obtain novel disturbance action controllers (DAC) with sub-linear data adaptive policy regret bounds that shrink when the trajectory of costs has small gradients, while staying sub-linear even in the worst case.

math.OC↗

arXiv2024

Fair Resource Allocation in Virtualized O-RAN Platforms

O-RAN systems and their deployment in virtualized general-purpose computing platforms (O-Cloud) constitute a paradigm shift expected to bring unprecedented performance gains. However, these architectures raise new implementation challenges and threaten to worsen the already-high energy consumption of mobile networks. This paper presents first a series of experiments which assess the O-Cloud's energy costs and their dependency on the servers' hardware, capacity and data traffic properties which, typically, change over time. Next, it proposes a compute policy for assigning the base station data loads to O-Cloud servers in an energy-efficient fashion; and a radio policy that determines at near-real-time the minimum transmission block size for each user so as to avoid unnecessary energy costs. The policies balance energy savings with performance, and ensure that both of them are dispersed fairly across the servers and users, respectively. To cater for the unknown and time-varying parameters affecting the policies, we develop a novel online learning framework with fairness guarantees that apply to the entire operation horizon of the system (long-term fairness). The policies are evaluated using trace-driven simulations and are fully implemented in an O-RAN compatible system where we measure the energy costs and throughput in realistic scenarios.

cs.NI↗

arXiv2024

Workflow Optimization for Parallel Split Learning

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 (FL). In a nutshell, SL splits the NN model into parts, and allows clients (devices) to offload the largest part as a processing task to a computationally powerful helper. In parallel SL, multiple helpers can process model parts of one or more clients, thus, considerably reducing the maximum training time over all clients (makespan). In this paper, we focus on orchestrating the workflow of this operation, which is critical in highly heterogeneous systems, as our experiments show. In particular, we formulate the joint problem of client-helper assignments and scheduling decisions with the goal of minimizing the training makespan, and we prove that it is NP-hard. We propose a solution method based on the decomposition of the problem by leveraging its inherent symmetry, and a second one that is fully scalable. A wealth of numerical evaluations using our testbed's measurements allow us to build a solution strategy comprising these methods. Moreover, we show that this strategy finds a near-optimal solution, and achieves a shorter makespan than the baseline scheme by up to 52.3%.

cs.DC↗

arXiv2023

Deep Reinforcement Learning for Orchestrating Cost-Aware Reconfigurations of vRANs

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 paper, a novel vRAN reconfiguration problem is formulated to jointly reconfigure the functional splits of the base stations (BSs), locations of the virtualized central units (vCUs) and distributed units (vDUs), their resources, and the routing for each BS data flow. The objective is to minimize the long-term total network operation cost while adapting to the varying traffic demands and resource availability. Testbed measurements are performed to study the relationship between the traffic demands and computing resources, which reveals high variance and depends on the platform and its load. Consequently, finding the perfect model of the underlying system is non-trivial. Therefore, to solve the proposed problem, a deep reinforcement learning (RL)-based framework is proposed and developed using model-free RL approaches. Moreover, the problem consists of multiple BSs sharing the same resources, which results in a multi-dimensional discrete action space and leads to a combinatorial number of possible actions. To overcome this curse of dimensionality, action branching architecture, which is an action decomposition method with a shared decision module followed by neural network is combined with Dueling Double Deep Q-network (D3QN) algorithm. Simulations are carried out using an O-RAN compliant model and real traces of the testbed. Our numerical results show that the proposed framework successfully learns the optimal policy that adaptively selects the vRAN configurations, where its learning convergence can be further expedited through transfer learning even in different vRAN systems. It offers significant cost savings by up to 59\% of a static benchmark, 35\% of DDPG with discretization, and 76\% of non-branching D3QN.

cs.NI↗

arXiv2023

Bandit Convex Optimisation Revisited: FTRL Achieves $\tilde{O}(t^{1/2})$ Regret

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 estimate. Plugging such a bandit estimator into the standard FTRL algorithm yields a bandit convex optimisation algorithm that achieves $\tilde{O}(t^{1/2})$ regret against adversarial time-varying convex loss functions.

cs.LG↗