Search

This paper introduces a dual-based algorithm framework for solving the regularized online resource allocation problems, which have potentially nonconcave cumulative rewards, hard resource constraints, and a nonseparable regularizer. Under a strategy of adaptively updating the resource constraints, the proposed framework only requests approximate solutions to the empirical dual problems up to a certain accuracy and yet delivers an optimal logarithmic regret under a locally second-order growth condition. Surprisingly, a delicate analysis of the dual objective function enables us to eliminate the notorious log-log factor in regret bound. The flexible framework renders renowned and computationally fast algorithms immediately applicable, for example, dual stochastic gradient descent. Additionally, an infrequent re-solving scheme is proposed, which significantly reduces computational demands without compromising the optimal regret performance. A worst-case square-root regret lower bound is established if the resource constraints are not adaptively updated during dual optimization, which underscores the critical role of adaptive dual variable update. Comprehensive numerical experiments demonstrate the merits of the proposed algorithm framework.

Model averaging is a widely adopted technique in federated learning (FL) that aggregates multiple client models to obtain a global model. Remarkably, model averaging in FL yields a superior global model, even when client models are trained with non-convex objective functions and on heterogeneous local datasets. However, the rationale behind its success remains poorly understood. To shed light on this issue, we first visualize the loss landscape of FL over client and global models to illustrate their geometric properties. The visualization shows that the client models encompass the global model within a common basin, and interestingly, the global model may deviate from the basin's center while still outperforming the client models. To gain further insights into model averaging in FL, we decompose the expected loss of the global model into five factors related to the client models. Specifically, our analysis reveals that the global model loss after early training mainly arises from i) the client model's loss on non-overlapping data between client datasets and the global dataset and ii) the maximum distance between the global and client models. Based on the findings from our loss landscape visualization and loss decomposition, we propose utilizing iterative moving averaging (IMA) on the global model at the late training phase to reduce its deviation from the expected minimum, while constraining client exploration to limit the maximum distance between the global and client models. Our experiments demonstrate that incorporating IMA into existing FL methods significantly improves their accuracy and training speed on various heterogeneous data setups of benchmark datasets. Code is available at https://github.com/TailinZhou/FedIMA. IEEE

Metaverse applications such as virtual reality (VR) content streaming, require optimal resource allocation strategies for mobile edge computing (MEC) to ensure a high-quality user experience. In contrast to online reinforcement learning (RL) algorithms, which can incur substantial communication overheads and longer delays, the majority of existing works employ offline-trained RL algorithms for resource allocation decisions in MEC systems. However, they neglect the impact of desynchronization between the physical and digital worlds on the effectiveness of the allocation strategy. In this paper, we tackle this desynchronization using a continual RL (CRL) framework that facilitates the resource allocation dynamically for MEC-enabled VR content streaming. We first design a digital twin-empowered edge computing (DTEC) system and formulate a quality of experience (QoE) maximization problem based on attention-based resolution perception. This problem optimizes the allocation of computing and bandwidth resources while adapting the attention-based resolution of the VR content. The CRL framework in DTEC enables adaptive online execution in a time-varying environment. We propose three variants of CRL, namely Continual Deep Deterministic Policy Gradient (CDDPG), Prioritized Experience Replay - CDDPG (PER-CDDPG), and Freshness Prioritized Experience Replay - CDDPG (FPER-CDDPG). We evaluate these algorithms, including two other benchmarks, using extensive experiments. FPER-CDDPG shows superior performance in terms of average latency, QoE, and successful delivery rate as well as meeting the hfQoE requirements over long-term execution while ensuring system scalability with the increasing number of users. IEEE

The Metaverse has emerged to extend our lifestyle beyond physical limitations. As essential components in the Metaverse, digital twins (DTs) are the real-time digital replicas of physical items. Multi-access edge computing (MEC) provides responsive services to the end users, ensuring an immersive and interactive Metaverse experience. While the digital representation (DT) of physical objects, end users, and edge computing systems is crucial in the Metaverse, the construction of these DTs and the interplay between them have not been well-investigated. In this article, we discuss the bidirectional reliance between the DT and the MEC system and investigate the creation of DTs of objects and users on the MEC servers and DT-assisted edge computing (DTEC). To ensure seamless handover among MEC servers and to avoid intermittent Metaverse services, we also explore the interaction between local DTECs on local MEC servers and the global DTEC on the cloud server due to the dynamic nature of network states (e.g., channel state and users' mobility). We investigate a continual learning framework for resource allocation strategy in local DTEC through a case study. Our strategy mitigates the desynchronization between physical-digital twins, ensures higher learning outcomes, and provides a satisfactory Metaverse experience. © 2018 IEEE.

With huge amounts of data generated from Internet of Things (IoT) devices, data-driven technologies are increasingly applied by firms to improve their IoT-based services in real time. To facilitate efficient utilization of the collected data, the design of data trading markets becomes crucial. Two important practical concerns are: 1) the data buyers arrive in a sequential and arbitrary manner and 2) a firm faces externalities when data is purchased by competing firms. In this article, we design a data trading marketplace for data buyers arriving dynamically in real time where the early arrived data buyers will exert negative externalities on the late arrivals within the same competition. Specifically, in market operations, when a data buyer arrives, it needs to submit a bid based on the price and the current externalities posted by the market operator. After receiving the bid, the market operator will announce the data allocation and payment as well as update the price. To construct the detailed market mechanism, we propose the allocation rule, payment rule, and price update method, which can be proven theoretically to guarantee the desirable properties, including incentive compatibility, individual rationality, revenue maximization, and computation efficiency. These theoretical conclusions are also validated via our numerical experiments. © 2014 IEEE.

Due to the massive computing demands of the Internet of Things, mobile edge computing (MEC) has been extensively investigated as a means of providing computation-intensive and latency-sensitive services at the network edge. With increasing density of base stations (BSs), users are simultaneously served by multiple BSs, leading to the multicell MEC environment. Intelligent reflecting surface (IRS) provides a promising solution for constructing the virtual Line-of-Sight (LoS) links between cell-edge users (CEUs) and BSs. In this article, we investigate the joint channel estimation and resource allocation in the IRS-aided multicell MEC system. Instead of assuming the perfect channel state information (CSI), we propose a three-phase channel estimation method to obtain the CSI. Our purpose is to minimize the total joint energy and latency cost (JELC) in terms of both task-execution latency and energy consumption in the IRS-aided multicell MEC problem by jointly optimizing the task offloading volume, precoding matrix, and IRS phase shifts. We propose a quadratically constrained program (QCP)-assisted proximal policy optimization (PPO) reinforcement learning algorithm with two modules (i.e., QCP optimizer and PPO agent) execute iteratively. The QCP optimizer is utilized to compute the offloading decision variables, and the PPO agent is adapted to determine the optimal channel precoding matrix and the phase shifts of IRS. Numerical results validate that our QCP-assisted PPO algorithm executes more rapidly than benchmarks. Moreover, the proposed QCP-assisted PPO algorithm delivers the best performance compared to benchmarks. Furthermore, the multicell IRS-aided MEC framework yields additional performance gains compared to those without IRS. © 2014 IEEE.

The explosive development of the Internet of Things (IoT) has led to increased interest in mobile edge computing (MEC), which provides computational resources at network edges to accommodate computation-intensive and latency-sensitive applications. Intelligent reflecting surfaces (IRSs) have gained attention as a solution to overcome blockage problems during the offloading uplink transmission in MEC systems. This paper explores IRS-aided multi-cell networks that enable servers to serve neighboring cells and cooperate to handle resource exhaustion. We aim to minimize the joint energy and latency cost by jointly optimizing the computation tasks, edge computing resources, user beamforming, and IRS phase shifts. The problem is decomposed into two subproblems - the MEC subproblem and the IRS communication subproblem - using the block coordinate descent (BCD) technique. The MEC subproblem is reformulated as a nonconvex quadratic constrained problem (QCP), while the IRS communication subproblem is transformed into a weight-sum-rate problem with auxiliary variables. We propose an efficient algorithm to alternately optimize the MEC resources and IRS communication variables. Numerical results show that our algorithm outperforms benchmarks and that multi-cell MEC systems achieve additional performance gains when supported by IRS. © 2017 IEEE.

Due to the influence of stochastic gradients, the existing algorithms suffer from slow convergence, noise explosion, and even failure to converge in practice, which motivates us to propose an accelerated algorithm to tackle these issues. Recognizing the potential of gradient, momentum, and conjugate gradient as promising search directions, we propose a 3-D acceleration algorithm, which uses a weighted combination of these three basis. Specifically, in order to analyze the dynamics of the discrete-time algorithm during the update process, we provide a general framework for approximating the discrete-time algorithm in the weak sense by a continuous-time stochastic differential equation. We exploit the continuous-time formulation together with Lyapunov drift optimization to derive novel adaptive step sizes, which effectively improve the performance of the algorithm in stabilizing noise and accelerating convergence. Extensive numerical experiments demonstrate the proposed algorithm’s superiority in convergence rate, computation complexity, and noise robustness compared to state-of-the-art baselines. IEEE

This letter explores the potential benefits of incorporating a bias voltage in the operation of an RF rectifier diode. Despite the challenges posed by network matching and additional power consumption, the study demonstrates efficiency enhancements across a range of input power levels. These enhancements offer significant advantages for active energy harvesters equipped with a controllable small bias source.

Federated learning allows multiple clients to collaboratively train a model without exchanging their data, thus preserving data privacy. Unfortunately, it suffers significant performance degradation due to heterogeneous data at clients. Common solutions involve designing an auxiliary loss to regularize weight divergence or feature inconsistency during local training. However, we discover that these approaches fall short of the expected performance because they ignore the existence of a vicious cycle between feature inconsistency and classifier divergence across clients. This vicious cycle causes client models to be updated in inconsistent feature spaces with more diverged classifiers. To break the vicious cycle , we propose a novel framework named Fed erated learning with F eature A nchors (FedFA). FedFA utilizes feature anchors to align features and calibrate classifiers across clients simultaneously. This enables client models to be updated in a shared feature space with consistent classifiers during local training. Theoretically, we analyze the non-convex convergence rate of FedFA. We also demonstrate that the integration of feature alignment and classifier calibration in FedFA brings a virtuous cycle between feature and classifier updates, which breaks the vicious cycle existing in current approaches. Extensive experiments show that FedFA significantly outperforms existing approaches on various classification datasets under label distribution skew and feature distribution skew.

A challenge of ambient backscatter communication (AmBC) systems is signal recovery because the transmitted information bits are embedded in the ambient RF signals and these are unknown and uncontrollable. To meet this challenge, averaging-based energy detectors are typically used but consequently the data rate is low and there is an error floor. Here we propose a new detection strategy based on the ratio between signals received from a multiple-antenna Reader. The advantage of using the ratio is that ambient RF signals are removed directly from the embedded signals without averaging and hence it can increase data rates and avoid the error floor. Different from the original ratio detector that uses the magnitude ratio of the signals between two Reader antennas, in our proposed approach, we utilize the complex ratio so that phase information is preserved and propose an accurate linear channel model approximation. This allows the application of existing linear detection techniques from which we can obtain a minimum distance detector and closed-form expressions for bit error rate (BER). Methods for the estimation of channel state information (CSI) are also provided. In addition, coding and interleaving are also included to further enhance the BER. The results are also general, allowing any number of Reader antennas to be utilized in the approach. Numerical results demonstrate the proposed approach performs better than approaches based on energy detection and the original ratio detectors. IEEE

Although deep neural networks (DNNs) have been remarkably successful in numerous areas, the performance of DNN is compromised in federated learning scenarios because of the large model size. A large model can induce huge communication overhead during the federated training, and also induce infeasible storage and computation burden at the clients during the inference. To address these issues, we investigate structured model compression in federated learning to construct sparse models with regular structure such that they require significantly less communication, storage and computation resources. We do this by proposing a three-layer hierarchical prior, which can promote a common regular sparse structure in the local models. We design a decentralized Turbo variational Bayesian inference (D-Turbo-VBI) algorithm to solve the resulting federated training problem. With the common regular sparse structure, both upstream and downstream communication overhead can be reduced, and the final model also has a regular sparse structure, which requires significantly less local storage and computation resources. Simulation results demonstrate that our proposed algorithm can efficiently reduce the communication overhead during federated training and the resulting model can achieve a significantly lower sparsity rate and inference time compared to the baselines while maintaining a competitive accuracy. IEEE

The continuously growing size of deep neural networks (DNNs) has sparked a surge in research on model compression techniques. Among these techniques, multi-resolution model compression has emerged as a promising approach which can generate multiple DNN models with shared weights and different computational complexity (resolution) through a single training. However, in most existing multi-resolution compression methods, the model structures for different resolutions are either predefined or uniformly controlled. This can lead to performance degradation as they fail to implement systematic compression to achieve the optimal model for each resolution. In this paper, we propose to perform multi-resolution compression from a Bayesian perspective. We design a resolution-aware likelihood and a two-layer prior for the channel masks, which allow joint optimization of the shared weights and the model structure of each resolution. To solve the resulted Bayesian inference problem, we develop a low complexity partial update block variational Bayesian inference (PUB-VBI) algorithm. Furthermore, we extend our proposed method into the arbitrary resolution case by proposing an auxiliary neural network (NN) to learn the mapping from the input resolution to the corresponding channel masks. Simulation results show that our proposed method can outperform the baselines on various NN models and datasets.