检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2022年第1期23卷 9893-9988页

作者： Alireza Fallah Mert Gürbüzbalaban Asuman Ozdaglar Umut Şimşekli Lingjiong Zhu Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge MA Department of Management Science and Information Systems Departments of Electrical Engineering and Statistics Rutgers University Piscataway NJ INRIA - Département d'Informatique de l' École Normale Supérieure PSL Research University Paris France Department of Mathematics Florida State University Tallahassee FL

We study distributed stochastic gradient (D-SG) method and its accelerated variant (D-ASG) for solving decentralized strongly convex stochastic optimization problems where the objective function is distributed over several computational units, lying on a fixed but arbitrary connected communication graph, subject to local communication constraints where noisy estimates of the gradients are available. We develop a framework which allows to choose the stepsize and the momentum parameters of these algorithms in a way to optimize performance by systematically trading off the bias, variance and dependence to network effects. When gradients do not contain noise, we also prove that D-ASG can achieve acceleration, in the sense that it requires O(√κlog(1/ε)) gradient evaluations and O(√κlog(1/ε)) communications to converge to the same fixed point with the non-accelerated variant where κ is the condition number and ε is the target accuracy. For quadratic functions, we also provide finer performance bounds that are tight with respect to bias and variance terms. Finally, we study a multistage version of D-ASG with parameters carefully varied over stages to ensure exact convergence to the optimal solution. It achieves optimal and accelerated O(-k/√κ) linear decay in the bias term as well as optimal O(σ2/k) in the variance term. We illustrate through numerical experiments that our approach results in accelerated practical algorithms that are robust to gradient noise and that can outperform existing methods.

关键词： distributed optimization accelerated methods stochastic optimization robustness multi-agent networks

来源：评论

学校读者我要写书评

暂无评论

Fueling the technology growth using innovative IoT solutions: The SmartBin project

Fueling the technology growth using innovative IoT solutions...

引用

2020 International Conference on Technology and Entrepreneurship, ICTE 2020

作者： Ziouzios, Dimitris Baras, Nikolaos Dasygenis, Minas Manavis, Athanasios Vanidis, Charilaos Tsanaktsidis, Constantinos Electrical and Computer Engineering University of Western Macedonia Kozani Greece Product and Systems Design Engineering University of Western Macedonia Kozani Greece Chemical Engineering University of Western Macedonia Kozani Greece

ISBN: (纸本)9781728149028

Cleanliness and recycling is a crucial matter for modern cities. As there is an obvious and increasing need to preserve valuable resources and reduce waste and pollution, research is vivid in this area. In this paper, we present our innovative project, the Smartbin, which is using state of the art approaches of Internet of Things (Iot) and waste classification. The design of the system permits the low-cost manufacturing of the final product, while uses state of the art technologies such as neural networks and the LoRaWAN protocol. We have implemented environmental friendly and low-cost Smart Bin prototypes, where the users can monitor each bin and be notified for incidents requiring their attention. The system also remotely transmits valuable data to the corresponding authorities, which can improve their effectiveness in waste management. © 2020 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Joint design of Radar Receive Filter and Unimodular ISAC Waveform with Sidelobe Level Control

arXiv

引用

arXiv 2025年

作者： Zhang, Kecheng Liu, Ya-Feng Wang, Zhongbin Yuan, Weijie Keskin, Musa Furkan Wymeersch, Henk Xia, Shuqiang School of System Design and Intelligent Manufacturing The Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen518055 China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China Department of Electrical Engineering Chalmers University of Technology Gothenburg41296 Sweden ZTE Corporation The State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen518055 China

Integrated sensing and communication (ISAC) has been considered a key feature of next-generation wireless networks. This paper investigates the joint design of the radar receive filter and dual-functional transmit waveform for the multiple-input multiple-output (MIMO) ISAC system. While optimizing the mean square error (MSE) of the radar receive spatial response and maximizing the achievable rate at the communication receiver, besides the constraints of full-power radar receiving filter and unimodular transmit sequence, we control the maximum range sidelobe level, which is often overlooked in existing ISAC waveform design literature, for better radar imaging performance. To solve the formulated optimization problem with convex and nonconvex constraints, we propose an inexact augmented Lagrangian method (ALM) algorithm. For each subproblem in the proposed inexact ALM algorithm, we custom-design a block successive upper-bound minimization (BSUM) scheme with closed-form solutions for all blocks of variable to enhance the computational efficiency. Convergence analysis shows that the proposed algorithm is guaranteed to provide a stationary and feasible solution. Extensive simulations are performed to investigate the impact of different system parameters on communication and radar imaging performance. Comparison with the existing works shows the superiority of the proposed algorithm. © 2025, CC BY-NC-SA.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

computer-integrated system of automatic balance control in centrifuge rotors with variable imbalance

Computer-integrated system of automatic balance control in c...

引用

International Conference on Modern electrical and Energy systems (MEES)

作者： Volodymyr Pavlenko Petro Kurliak Serhiy Horiashchenko Oleksii Volianyk Yaroslav Batsala Tetiana Nikitchuk Department of Information and Computer Technologies Kyiv National University of Technologies and Design Kyiv Ukraine Department of Electrical Power Engineering Ivano-Frankivsk National Technical University of Oil and Gas Ivano-Frankivsk Ukraine Department of Machines and Devices Electromechanical and Energy Systems Khmelnytskyi National University Khmelnytskyi Ukraine Department of Mechanical Engineering Kyiv National University of Technologies and Design Kyiv Ukraine Department of Computer Technologies in Medicine and Telecommunications Zhytomyr Polytechnic State University Zhytomyr Ukraine

The paper presents the developed computer-integrated system of automatic control of rotors balancing in centrifuges with variable imbalance. It includes a microcontroller, a Hall sensor, a computer-oriented Bond Graph model of an asynchronous motor, and a control program that, according to the proposed algorithm, checks the nominal and critical value of the centrifuge drive current. At the same time, the current values are recorded and the current is monitored. When the current increases, the system automatically resets the revolutions by 10% to reduce the amplitude of vibrations in the transient modes of their rotation with further control of the permissible current limit and engine load.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bayesian Optimization Framework for Efficient Fleet design in Autonomous Multi-Robot Exploration

arXiv

引用

arXiv 2024年

作者： Concha, David Molina Li, Jiping Yin, Haoran Park, Kyeonghyeon Lee, Hyun-Rok Lee, Taesik Sirohi, Dhruv Lee, Chi-Guhn The Dynamic Optimization and Reinforcement Learning Laboratory The Department of Mechanical & Industrial Engineering University of Toronto TorontoONM5S3G8 Canada The Department of Electrical & Computer Engineering University of Toronto TorontoONM5S3G8 Canada The Division of Engineering Science The Faculty of Applied Science and Engineering University of Toronto TorontoONM5S3G8 Canada The Complex System Design Laboratory The Department of Industrial and Systems Engineering Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of The Department of Industrial Engineering Inha University Incheon22212 Korea Republic of

This study addresses the challenge of fleet design optimization in the context of heterogeneous multi-robot fleets, aiming to obtain feasible designs that balance performance and costs. In the domain of autonomous multi-robot exploration, reinforcement learning agents play a central role, offering adaptability to complex terrains and facilitating collaboration among robots. However, modifying the fleet composition results in changes in the learned behavior, and training multi-robot systems using multi-agent reinforcement learning is expensive. Therefore, an exhaustive evaluation of each potential fleet design is infeasible. To tackle these hurdles, we introduce Bayesian Optimization for Fleet design (BOFD), a framework leveraging multiobjective Bayesian Optimization to explore fleets on the Pareto front of performance and cost while accounting for uncertainty in the design space. Moreover, we establish a sub-linear bound for cumulative regret, supporting BOFD’s robustness and efficacy. Extensive benchmark experiments in synthetic and simulated environments demonstrate the superiority of our framework over state-of-the-art methods, achieving efficient fleet designs with minimal fleet evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Learning-based Sustainable Multi-User Computation Offloading for Mobile Edge-Quantum Computing

arXiv

引用

arXiv 2022年

作者： Xu, Minrui Niyato, Dusit Kang, Jiawen Xiong, Zehui Chen, Mingzhe School of Computer Science and Engineering Nanyang Technological University Singapore School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States

In this paper, a novel paradigm of mobile edge-quantum computing (MEQC) is proposed, which brings quantum computing capacities to mobile edge networks that are closer to mobile users (i.e., edge devices). First, we propose an MEQC system model where mobile users can offload computational tasks to scalable quantum computers via edge servers with cryogenic components and fault-tolerant schemes. Second, we show that it is NP-hard to obtain a centralized solution to the partial offloading problem in MEQC in terms of the optimal latency and energy cost of classical and quantum computing. Third, we propose a multi-agent hybrid discrete-continuous deep reinforcement learning using proximal policy optimization to learn the long-term sustainable offloading strategy without prior knowledge. Finally, experimental results demonstrate that the proposed algorithm can reduce at least 30% of the cost compared with the existing baseline solutions under different system settings. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Towards Communication-efficient Federated Learning via Sparse and Aligned Adaptive Optimization

arXiv

引用

arXiv 2024年

作者： Deng, Xiumei Li, Jun Wei, Kang Shi, Long Xiong, Zeihui Ding, Ming Chen, Wen Jin, Shi Poor, H. Vincent School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China The Department of Computing Hong Kong Polytechnic University 999077 Hong Kong The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Data61 CSIRO SydneyNSW2015 Australia Department of Electronics Engineering Shanghai Jiao Tong University Shanghai200240 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China Department of Electrical and Computer Engineering Princeton University NJ08544 United States

Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However, federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead compared to federated SGD (FedSGD) algorithms, which arises from the necessity to transmit both local model updates and first and second moment estimates from distributed devices to the centralized server for aggregation. Driven by this issue, we propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates of local model parameters and moment estimates and subsequently upload the sparse representations to the centralized server. To further reduce the communication overhead, the updates of local model parameters and moment estimates incorporate a shared sparse mask (SSM) into the sparsification process, eliminating the need for three separate sparse masks. Theoretically, we develop an upper bound on the divergence between the local model trained by FedAdam-SSM and the desired model trained by centralized Adam, which is related to sparsification error and imbalanced data distribution. By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error. Additionally, we provide convergence bounds for FedAdam-SSM in both convex and non-convex objective function settings, and investigate the impact of local epoch, learning rate and sparsification ratio on the convergence rate of FedAdam-SSM. Experimental results show that FedAdam-SSM outperforms baselines in terms of convergence rate (over 1.1× faster than the sparse FedAdam baselines) and test accuracy (over 14.5% ahead of the quantized FedAdam baselines). Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts-Enabled Parallel Scheduling and Processing for Vehicular Generative AI Services

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Xie, Gaochang Xiong, Zehui Xie, Renchao Deng, Xiumei Guo, Song Guizani, Mohsen Han, Zhu Beijing University of Posts and Telecommunication State Key Laboratory of Networking and Switching Technology Beijing 100876 China Purple Mountain Laboratories Nanjing 211111 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong Mohammad Bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates University of Houston Department of Electrical and Computer Engineering Houston 77004 TX United States Kyung Hee University Department of Computer Science and Engineering Seoul 446-701 South Korea

Foundation models (FMs) have revolutionized generative AI (GAI) lifecycle with their pre-trained intelligence capabilities. While the recent success of web-based models like GPT-4 has spurred interest in extending FMs to edge scenarios like the Internet of Vehicles (IoV), challenges such as data privacy, network congestion, and limited edge resource awareness hinder the direct application of cloud-based FMs. To address these challenges, this paper reconfigures the mixture of experts (MoE) architecture to deploy Transformer-based FM experts across vehicles for distributed GAI inference. Specifically, we propose an MoE-empowered vehicular FM system with two key innovations: a physical gating network that dynamically adapts to wireless environments, and a vehicle-to-vehicle (V2V) communication-based expert parallelism mechanism to enhance efficiency and resource utilization. Then, we formulate the communication, computation, and memory models for analyzing inference latency. Furthermore, to optimize the computational resource allocation for enhancing inference performance, we establish a Stackelberg game and propose the Gradient Ascent and Evolutionary Optimization-based Competitive Pricing and Allocation (GECPA) algorithm, which balances resource allocation and usage costs by combining the rapid convergence of gradient ascent with the broader exploration capability of evolutionary optimization. Simulation results demonstrate the superior parallel processing efficiency and reduced latency of the proposed MoE-based FM inference scheme. Compared with the best-performing benchmark algorithm, GECPA improves the average utility of infrastructure vehicles by up to 2.01 times, reduces inference latency by 16.58%, and increases the successful execution rate of GAI tasks by 10.66%, thereby achieving a better balance between efficiency and incentive compatibility in dynamic IoV environments. © 2015 IEEE.

关键词： expert parallelism foundation models (FMs) Generative AI (GAI) Internet of Vehicles (IoV) mixture of experts (MoE) resource allocation

来源：评论

学校读者我要写书评

暂无评论

EPViSA: Efficient Auction design for Real-time Physical-Virtual Synchronization in the Metaverse

arXiv

引用

arXiv 2022年

作者： Xu, Minrui Niyato, Dusit Wright, Benjamin Zhang, Hongliang Kang, Jiawen Xiong, Zehui Mao, Shiwen Han, Zhu School of Computer Science and Engineering Nanyang Technological University Singapore308232 Singapore Department of Mathematics Massachusetts Institute of Technology CambridgeMA02139 United States Department of Electrical and Computer Engineering Princeton University PrincetonNJ08544 United States School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States Department of Electrical and Computer Engineering University of Houston HoustonTX77004 United States Department of Computer Science and Engineering Kyung Hee University Seoul446-701 Korea Republic of

Metaverse can obscure the boundary between the physical and virtual worlds. Specifically, for the Metaverse in vehicular networks, i.e., the vehicular Metaverse, vehicles are no longer isolated physical spaces but interfaces that extend the virtual worlds to the physical world. Accessing the Metaverse via autonomous vehicles (AVs), drivers and passengers can immerse in and interact with 3D virtual objects overlaying views of streets on head-up displays (HUD) via augmented reality (AR). The seamless, immersive, and interactive experience rather relies on real-time multi-dimensional data synchronization between physical entities, i.e., AVs, and virtual entities, i.e., Metaverse billboard providers (MBPs). However, mechanisms to allocate and match synchronizing AV and MBP pairs to roadside units (RSUs) in a synchronization service market, which consists of the physical and virtual submarkets, are vulnerable to adverse selection. In this paper, we propose an enhanced second-score auction-based mechanism, named EPViSA, to allocate physical and virtual entities in the synchronization service market of the vehicular Metaverse. The EPViSA mechanism can determine synchronizing AV and MBP pairs simultaneously while protecting participants from adverse selection and thus achieving high total social welfare. We propose a synchronization scoring rule to eliminate the external effects from the virtual submarkets. Then, a price scaling factor is introduced to enhance the allocation of synchronizing virtual entities in the virtual submarkets. Finally, rigorous analysis and extensive experimental results demonstrate that EPViSA can achieve at least 96% of the social welfare compared to the omniscient benchmark while ensuring strategy-proof and adverse selection free through a simulation testbed. © 2022, CC BY.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Symmetrical Joint Learning Support-query Prototypes for Few-shot Segmentation

arXiv

引用

arXiv 2024年

作者： Li, Qun Sun, Baoquan Xiao, Fu Qi, Yonggang Bhanu, Bir School of Computer Science Nanjing University of Posts and Telecommunications 9 Wenyuan Road Jiangsu Nanjing210023 China Information Systems Technology and Design Pillar Singapore University of Technology and Design 8 Somapah Road 487372 Singapore School of Artificial Intelligence Beijing University of Posts and Telecommunications 10 Xitucheng Road Beijing100876 China Department of Electrical and Computer Engineering University of California at Riverside 900 University Avenue RiversideCA92521 United States

We propose Sym-Net, a novel framework for Few-Shot Segmentation (FSS) that addresses the critical issue of intra-class variation by jointly learning both query and support prototypes in a symmetrical manner. Unlike previous methods that generate query prototypes solely by matching query features to support prototypes, which is a form of bias learning towards the few-shot support samples, Sym-Net leverages a balanced symmetrical learning approach for both query and support prototypes, ensuring that the learning process does not favor one set (support or query) over the other. One of main modules of Sym-Net is the visual-text alignment based prototype aggregation module, which is not just query-guided prototype refinement, it is a jointly learning from both support and query samples, which makes the model beneficial for handling intra-class discrepancies and allows it to generalize better to new, unseen classes. Specifically, a parameter-free prior mask generation module is designed to accurately localize both local and global regions of the query object by using sliding windows of different sizes and a self-activation kernel to suppress incorrect background matches. Additionally, to address the information loss caused by spatial pooling during prototype learning, a top-down hyper-correlation module is integrated to capture multi-scale spatial relationships between support and query images. This approach is further jointly optimized by implementing a co-optimized hard triplet mining strategy. Experimental results show that the proposed Sym-Net outperforms state-of-the-art models, which demonstrates that jointly learning support-query prototypes in a symmetrical manner for FSS offers a promising direction to enhance segmentation performance with limited annotated data. The code is available at: https://***/Sunbaoquan/Sym-Net. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：