Once-for-All (OFA) training enables a single super-net to generate multiple sub-nets tailored to diverse deployment scenarios, supporting flexible trade-offs among accuracy, robustness, and model-size without retraining. However, as the number of supported sub-nets increases, excessive parameter sharing in the backbone limits representational capacity, leading to degraded calibration and reduced overall performance. To address this, we propose SOLAR (Switchable Output Layer for Accuracy and Robustness in Once-for-All Training), a simple yet effective technique that assigns each sub-net a separate classification head. By decoupling the logit learning process across sub-nets, the Switchable Output Layer (SOL) reduces representational interference and improves optimization, without altering the shared backbone. We evaluate SOLAR on five datasets (SVHN, CIFAR-10, STL-10, CIFAR-100, and TinyImageNet) using four super-net backbones (ResNet-34, WideResNet-16-8, WideResNet-40-2, and MobileNetV2) for two OFA training frameworks (OATS and SNNs). Experiments show that SOLAR outperforms the baseline methods: compared to OATS, it improves accuracy of sub-nets up to 1.26%, 4.71%, 1.67%, and 1.76%, and robustness up to 9.01%, 7.71%, 2.72%, and 1.26% on SVHN, CIFAR-10, STL-10, and CIFAR-100, respectively. Compared to SNNs, it improves TinyImageNet accuracy by up to 2.93%, 2.34%, and 1.35% using ResNet-34, WideResNet-16-8, and MobileNetV2 backbones (with 8 sub-nets), respectively. The code of SOLAR is publicly available at: https://github.com/NAIL-UH/SOLAR and its website can be accessed at https://saktx.github.io/solar.github.io/.

Space-air-ground integrated networks can provide better connectivity and improved performance to ground users and thus have been well-recognized as the innovative trend for future 6G and beyond wireless systems. However, such heterogeneous and complex integrated communication systems also pose many new challenges for joint performance optimization. In this paper, we study the data delivery optimization problem in a space-air-ground network, where joint resource management decisions on user association, bandwidth allocation, cache placement, and high-altitude platform (HAP) location selection have to be optimized. To tackle this complex and challenging mixed integer programming optimization problem, we introduce a quantum-assisted method, named the Hybrid quantum-classical Benders’ Decomposition (HyBD) algorithm, which leverages the strengths of both quantum and classical computing. Experiments on the commercial quantum annealing machine demonstrate the effectiveness and robustness of the proposed HyBD method, with up to 64.3% improvement of iteration number and 82.8% improvement of average computation time over the classical Benders’ Decomposition algorithm on classical CPUs even at small scales, which demonstrates the quantum advantage.

In the era of 6G and beyond, space-aerial-terrestrial quantum networks (SATQNs) are poised to advance the development of a global-scale quantum Internet. These networks leverage free space optical satellite and aerial quantum networks to complement optical fiber-based terrestrial quantum networks to enable the distribution of high-fidelity quantum entanglement over long distances. However, establishing multi-hop end-to-end quantum entanglement remains highly challenging, not only due to time-varying link conditions and structural heterogeneity inherent in SATQNs, but also because noise in quantum channels and imperfections in quantum operations can degrade the quality of entanglement. To address this challenge, we formulate an optimization problem that maximizes SATQN throughput by jointly optimizing routing path selection and entanglement generation rates (PS-EGR) while ensuring high entanglement fidelity. The resulting problem is a mixed-integer linear programming (MILP) formulation, which is NP-hard. We propose a Benders’ decomposition (BD)-based approach to solve this problem efficiently. Specifically, the MILP is decomposed into a master problem for binary routing path selection and a subproblem for continuous entanglement generation rate optimization. Numerical results validate the effectiveness of the proposed PS-EGR scheme, offering critical insights into the optimization and deployment of SATQNs.

This paper addresses a distributed leader-follower formation control problem for a group of agents, each using a body-fixed camera with a limited field of view (FOV) for state estimation. The main challenge arises from the need to coordinate the agents' movements with their cameras' FOV to maintain visibility of the leader for accurate and reliable state estimation. To address this challenge, we propose a novel perception-aware distributed leader-follower safe control scheme that incorporates FOV limits as state constraints. A Control Barrier Function (CBF) based quadratic program is employed to ensure the forward invariance of a safety set defined by these constraints. Furthermore, new neural network based and double bounding boxes based estimators, combined with temporal filters, are developed to estimate system states directly from real-time image data, providing consistent performance across various environments. Comparison results in the Gazebo simulator demonstrate the effectiveness and robustness of the proposed framework in two distinct environments.

We develop an open-source, end-to-end software (named QHDOPT), which can solve nonlinear optimization problems using the quantum Hamiltonian descent (QHD) algorithm. QHDOPT offers an accessible interface and automatically maps tasks to various supported quantum backends (i.e., quantum hardware machines). These features enable users, even those without prior knowledge or experience in quantum computing, to utilize the power of existing quantum devices for nonlinear and nonconvex optimization tasks. In its intermediate compilation layer, QHDOPT employs SimuQ, an efficient interface for Hamiltonian-oriented programming, to facilitate multiple algorithmic specifications and ensure compatible cross-hardware deployment. The detailed documentation of QHDOPT is available at https://github.com/jiaqileng/QHDOPT . History: Accepted by Giacomo Nannicini, Area Editor for Quantum Computing and Operations Research. Accepted for Special Issue. Funding: This work was supported by the U.S. Department of Energy’s Advanced Research Projects Agency–Energy [Grant DE-SC0020273], the Alfred P. Sloan Foundation, the Simons Foundation [Simons Investigator Award 825053], the Simons Quantum Postdoctoral Fellowship, the National Science Foundation [Grants CCF-1816695, CCF-1942837, and ECCS-2045978], the Unitary Fund, and the Air Force Office of Scientific Research [Grant FA95502110051]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2024.0587 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2024.0587 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Advanced AI-Generated Content (AIGC) technologies have injected new impetus into teleoperation, enhancing its security and efficiency. Edge AIGC networks have been introduced to meet the stringent low-latency requirements of teleoperation. However, the inherent uncertainty of AIGC service quality and the need to incentivize AIGC service providers (ASPs) make the design of a robust incentive mechanism essential. This design is particularly challenging due to uncertainty and information asymmetry, as teleoperators have limited knowledge of the remaining resource capacities of ASPs. To this end, we propose a distributionally robust optimization (DRO)-based contract theory to design robust reward schemes for AIGC task offloading. Notably, our work extends the contract theory by integrating DRO, addressing the fundamental challenge of contract design under uncertainty. In this paper, we employ contract theory to model information asymmetry while utilizing DRO to capture the uncertainty in AIGC service quality. Given the inherent complexity of the original DRO-based contract theory problem, we reformulate it into an equivalent, tractable bi-level optimization problem. To efficiently solve this problem, we develop a Block Coordinate Descent (BCD)-based algorithm to derive robust reward schemes. Simulation results on our unitybased teleoperation platform demonstrate that the proposed method improves teleoperator utility by 2.7% to 10.74% under varying degrees of AIGC service quality shifts and increases ASP utility by 60.02% compared to the SOTA method, i.e., Deep Reinforcement Learning (DRL)-based contract theory. The code and data are publicly available at https://github.com/Zijun0819/DROContract-Theory

Network function virtualization (NFV)-enabled space information network (SIN) has emerged as a promising method to facilitate global coverage and seamless service. This paper proposes a novel NFV-enabled SIN to provide end-to-end communication and computation services for ground users. Based on the multi-functional time expanded graph (MF-TEG), we jointly optimize the user association, virtual network function (VNF) deployment, and flow routing strategy (U-VNF-R) to maximize the total processed data received by users. The original problem is a mixed-integer linear program (MILP) that is intractable for classical computers. Inspired by quantum computing techniques, we propose a hybrid quantum-classical Benders’ decomposition (HQCBD) algorithm. Specifically, we convert the master problem of the Benders’ decomposition into the quadratic unconstrained binary optimization (QUBO) model and solve it with quantum computers. To further accelerate the optimization, we also design a multi-cut strategy based on the quantum advantages in parallel computing. Numerical results demonstrate the effectiveness and efficiency of the proposed algorithm and U-VNF-R scheme.

In the era of Internet of Things (IoT), multi-access edge computing (MEC)-enabled satellite-aerial-terrestrial integrated network (SATIN) has emerged as a promising technology to provide massive IoT devices with seamless and reliable communication and computation services. This paper investigates the cooperation of low Earth orbit (LEO) satellites, high altitude platforms (HAPs), and terrestrial base stations (BSs) to provide relaying and computation services for vastly distributed IoT devices. Considering the uncertainty in dynamic SATIN systems, we formulate a stochastic optimization problem to minimize the time-average expected service delay by jointly optimizing resource allocation and task offloading while satisfying the energy constraints. To solve the formulated problem, we first develop a Lyapunov-based online control algorithm to decompose it into multiple one-slot problems. Since each one-slot problem is a large-scale mixed-integer nonlinear program (MINLP) that is intractable for classical computers, we further propose novel hybrid quantum-classical generalized Benders’ decomposition (HQCGBD) algorithms to solve the problem efficiently by leveraging quantum advantages in parallel computing. Numerical results validate the effectiveness of the proposed MEC-enabled SATIN schemes.

The rapid advancement of machine learning (ML) and the growing need for computational power have led to the exploration of quantum computing, which offers significant potential for faster complex calculations. However, Quantum Machine Learning (QML) faces challenges due to the limited number of qubits and noise of quantum circuits, particularly with Noisy Intermediate-Scale Quantum (NISQ) devices. These challenges severely limit the current capacity to train accurate and stable Quantum Machine Learning Models. In this paper, we propose a novel framework for QML that employs the knowledge distillation method to harness the power of well-trained classical machine learning (CML) models and enhance the training performance of QML models. In this framework, we utilize the well-trained CML as a teacher model to assist the training of the student QML model using the knowledge distillation method. By distilling knowledge from the robust CML model, our framework can potentially address the problem of the barren plateau which hinders effective model training. Knowledge distillation is well suited for this framework through the transfer of knowledge without parameter sharing. Through empirical tests, our framework has demonstrated not only an increase in the accuracy of QML models but also a notable improvement in training stability.

Benders' decomposition (BD) algorithm constitutes a powerful mathematical programming method of solving mixed-integer linear programming (MILP) problems with a specific block structure. Nevertheless, BD still needs to solve an NP-hard quasi-integer programming master problem (MAP), which motivates us to harness the popular variational quantum algorithm (VQA) to assist BD. More specifically, we choose the popular quantum approximate optimization algorithm (QAOA) of the VQA family. We transfer the BD's MAP into a digital quantum circuit associated with a physically tangible problem-specific ansatz; and then solve it with the aid of a state-of-the-art digital quantum computer. Next, we evaluate the computational results and discuss the feasibility of the proposed algorithm. The hybrid approach advocated, which utilizes both classical and digital quantum computers, is capable of tackling many practical MILP problems in communication and networking, as demonstrated by a pair of case studies.

Numerous optimization scenarios such as industrial production planning, network communication routing, and logistic scheduling can be modeled as large-scale integer linear programming problems. However, due to the NP-Hardness of these problems, it is very challenging to optimally solve these problems in a short time on classical computers. Quantum computers have emerged as a new computing platform to provide new computing paradigms to tackle these problems. However, the scalability and efficiency of current quantum computers pose significant challenges in practical implementations of quantum optimization algorithms. In this paper, we propose a novel hybrid quantum-classical approach, termed Hybrid quantum-classical Dantzig-Wolfe Decomposition (HyDWD), aimed at solving these problems. In this framework, the subproblems can be solved in parallel on quantum computers. Our results demonstrate the benefits of integrating parallel quantum computing with the proposed hybrid quantum-classical framework via Dantzig-Wolfe decomposition, paving the way for advancements in optimization and decision-making processes.

The development of integrated satellite-terrestrial networks has gained significant attention from both industry and academia in recent years, owing to their potential for delivering low latency, high dependability, strong resilience, ubiquitous connectivity and global broadband coverage services. However, due to the ever-changing nature of satellite topology and the complexity of diverse integrated satellite-terrestrial networks, routing requests is challenging. In this paper, the vehicle movement is uncertain introducing the intermittent connectivity related to vehicles. Therefore, we propose a distributionally robust optimization (DRO) model to minimize, under uncertain latency probability distributions, the expected worst-case overall task routing delay from source to target user equipment through satellite constellation. The model addresses undetermined uploading and downloading latency between automobiles, satellites, and user equipment by employing the Wasserstein ambiguity set, allowing for unpredictable vehicle mobility and intermittent connections. By reformulating the problem into a tractable form, we determine the optimal routing path for task uploading, satellite constellation, and task downloading. Ultimately, the performance of the proposed DRO model demonstrates the model’s ability to address the challenges of integrated satellite-terrestrial network routing.

The advancement of satellite-based quantum networks shows promise in transforming global communication infrastructure by establishing a secure and reliable quantum Internet. These networks use optical signals from satellites to ground stations to distribute high-fidelity quantum entanglements over long distances, overcoming the limitations of traditional terrestrial systems. However, the complexity of satellite-based entanglement distribution and terrestrial quantum swapping in the integrated network requires joint optimization with satellite assignment, resource allocation, and path selection. To address this challenge, we introduce a hybrid quantum-classical algorithm to solve the optimization problem by leveraging the strengths of both quantum and classical computing. The original problem is decomposed into a master problem and several subproblems using Dantzig-Wolfe decomposition and linearization techniques. Through experiments, this study demonstrates the effectiveness and reliability of the proposed methods in optimizing large-scale networks and managing qubit usage compared to the classical optimization techniques. The findings provide valuable insights for designing and implementing satellite-based entanglement distribution in quantum networks, paving the way for a secure global quantum communication infrastructure.

Due to the ability to provide low latency, high dependability, and worldwide broadband coverage services, the development of integrated satellite-terrestrial networks has attracted significant interest from both industry and academia over the past few decades. However, the dynamic satellite topology, heterogeneous, expansive, and intricate properties of the integrated satellite-terrestrial network make routing tasks difficult. In this research, we design the distributionally robust optimization (DRO) model with the objective of minimizing the estimated worst-case total task routing delay from the source mobile devices to the matching target mobile devices under an uncertain probability distribution. Taking into account the unpredictable vehicle movement and discontinuous connection between vehicles and mobile devices, the indeterminate offloading and downloading from automobiles to satellites and mobile devices, respectively, are captured by the Wasserstein ambiguity set. Then, we are able to determine the optimal route for task uploading, routing throughout the satellite constellation, and downloading. Finally, experimental results demonstrate that our proposed model has a lower and more robust latency than that of robust optimization (RO) strategy.

The scheduling problem for federated learning (FL) with multiple models in a distributed network is challenging, as it involves NP-hard mixed-integer nonlinear programming. Moreover, it requires optimal participant selection and learning rate determination among multiple FL models to avoid high training costs and resource competition. To overcome those chal-lenges, in literature the Benders' decomposition algorithm (BD) can deal with mixed integer problems, however, it still suffers from limited scalability. To address this issue, in this paper, we present the Hybrid Quantum-Classical Benders' Decomposition (HQCBD) algorithm, which combines the power of quantum and classical computing to solve the joint participant selection and learning scheduling problem in multi-model FL. HQCBD decomposes the optimization problem into a master problem with binary variables and small subproblems with continuous variables. This collaboration maximizes the potential of both quantum and classical computing, and optimizes the complex joint optimization problem. Simulation on the commercial D-Wave quantum annealing machine demonstrates the effectiveness and robustness of the proposed method, with up to 18% improvement of iterations and 81% improvement of computation time over BD algorithm on classical CPUs even at small scales.

Accurately localizing 1D signal patterns, such as Gamma-ray well-log depth matching, is crucial in the oilfield service industry as it directly affects the quality of oil and gas exploration. However, traditional methods such as well-log curve analysis and pattern hand-picking matching are labor-intensive and heavily rely on human expertise, leading to inconsistent results. Although attempts have been made to automate this process, challenges such as low computational performance, non-robustness, and non-generalization remain unsolved. To address these challenges, we have developed a data-driven AI system that learns an active signal pattern localization strategy inspired by human attention. Our artificial intelligence system uses an offline reinforcement learning (RL) framework as its central component, which solves a highly abstracted Markov decision process problem via offline training on human-labeled historical data. The RL agent uses top-down reasoning to determine the location of target signal fragments by deforming a bounding window using simple transformation actions. To overcome distribution shifts between logged data and real and ensure generalization, we propose a discrete distributionally robust soft actor-critic RL framework (DRSAC-Discrete) to solve the Markov decision process problem under uncertainty. By exploring unfamiliar environments in a restrictive manner, the DRSAC-Discrete algorithm provides a safe solution that can be used when data is limited during the early stage of this industrial application. We evaluated the reinforcement learning-based localization system on augmented field Gamma-ray well-log datasets, and the results showed promising localization capability. Furthermore, the DRSAC-Discrete algorithm demonstrated relatively robust performance guarantees when facing data shortage.

With the explosive growth of low earth orbit (LEO) satellite networks, such as Starlink, satellite communication has lower latency and can achieve high-speed transmission than before. However, the time-variant topology during all network lifetimes makes the routing problem in the LEO satellite networks challenging. Therefore, in this paper, we propose the deep reinforcement learning-based satellite routing (DRL-SR) method to tackle the multi-commodity flow routing problem in the LEO satellite networks. Given the current state of the satellite network environment, the satellite operation center will determine how to route the requests to the matching destinations. Particularly, the single agent in our DRL-SR approach can determine the multiple next hops as actions for all the corresponding requests each timeslot. Finally, simulation results show that our proposed algorithm yields lower latency than the shortest path approach.

The Benders’ decomposition algorithm is a technique in mathematical programming for complex mixed-integer linear programming (MILP) problems with a particular block structure. The strategy of Benders’ decomposition can be described as a strategy of divide and conquer. The Benders’ decomposition algorithm has been employed in a variety of applications such as communication, networking, and machine learning. However, the master problem in Benders’ decomposition is still NP-hard, which motivates us to employ quantum computing. In the paper, we propose a hybrid quantum-classical Benders’ decomposition algorithm. We transfer the Benders’ decomposition’s master problem into the quadratic unconstrained binary optimization (QUBO) model and solve it by the state-of-the-art quantum annealer. Then, we analyze the computational results and discuss the feasibility of the proposed algorithm. Due to our reformulation in the master problem in Benders’ decomposition, our hybrid algorithm, which takes advantage of both classical and quantum computers, can guarantee the solution quality for solving MILP problems.

Network function virtualization (NFV) is a crucial technology for the 5G network development because it can improve the flexibility of employing hardware and reduce the construction of base stations. There are vast service chains in NFV to meet users’ requests, which are composed of a sequence of network functions. These virtual network functions (VNFs) are implemented in virtual machines by software and virtual environment. How to deploy VMs to process VNFs of the service chains as soon as possible when users’ requests are received is very challenging to solve by traditional algorithms on a large scale. Compared with traditional algorithms, quantum computing has better computational performance because of quantum parallelism. We build an integer linear programming model of the VNF scheduling problem with the objective of minimizing delays, and transfer it into the quadratic unconstrained binary optimization (QUBO) model. Our proposed heuristic algorithm employs a quantum annealer to solve the model. Finally, we evaluate the computational results and explore the feasibility of leveraging quantum computing to solve the VNF scheduling problem.

Implementing wireless body area networks (WBANs) is very challenging, due to limited power supply, inadequate computation capability, and imperfect channel state information (CSI). In this paper, we propose a hybrid offloading scheme with backscatter communication (BackCom) under imperfect CSI, where each sensor firstly receives radio frequency (RF) energy and then offloads body data task via low-power BackCom to the access point (AP) for edge computing. Aiming to minimize the end-to-end system latency, we jointly optimize the computation speed of AP for processing computation tasks, the power of the signal transmitted by the AP, and the power reflection coefficient under energy and data rate chance constraints. To solve the proposed distributionally robust chance-constrained optimization problem, we approximate chance constraints by the Bernstein-type-inequality (BTI) method and Conditional value-at-risk (CVaR) method in the Gaussian distribution and arbitrary distribution of channel estimation errors, respectively. To tackle the NP-hard problem efficiently, the original problem can be decomposed into two subproblems, which are solved by successive linear programming and iterative algorithm, respectively. Simulation results show that the CVaR method outperforms the other methods for the non-Gaussian CSI mismatch, and the Bernstein method is more suitable for the Gaussian distribution of CSI errors.

Look-ahead unit commitment (LAUC) is recently introduced among independent system operators (ISOs) in the U.S. to increase generation capacity by committing more generators after day-ahead unit commitment when facing various uncertainties in the power system operations. However, as the share of intermittent renewable energy increases significantly in the power generation portfolio, the load continues to fluctuate, and unexpected events and market behaviors happen nowadays, the ISOs are facing new critical challenges to maintain the reliability of power system. To systematically manage these uncertainties and corresponding challenges, new advanced approaches are urgently required to improve current LAUC models and solution methods. Therefore, in this paper, we first propose a new formulation to represent forbidden zones and dynamic ramping rate limits, which help capture the system operation status more accurately and hedge against the uncertainties more effectively, and then correspondingly propose a data-driven risk-averse LAUC model. Our computational experiments show how the size of data influences operational decisions and how the inclusion of forbidden zones and dynamic ramping provide better decisions.