检索结果-内蒙古大学图书馆

Abstracts of the 2025 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems

作者： Benjamin Moseley Heather Newman Kirk Pruhs Rudy Zhou Carnegie Mellon University Pittsburgh PA USA University of Pittsburgh Pittsburgh PA USA Supply Chain Optimization Technologies Microsoft Washington DC USA

ISBN: (纸本)9798400715938

A common theme in stochastic optimization problems is that, theoretically, stochastic algorithms need to "know" relatively rich information about the underlying distributions. This is at odds with most applications, where distributions are rough predictions based on historical data. Thus, commonly, stochastic algorithms are making decisions using imperfect predicted distributions, while trying to optimize over some unknown true *** consider the fundamental problem of scheduling stochastic jobs preemptively on a single machine to minimize expected mean completion time in the setting where the scheduler is only given imperfect predicted job size distributions. If the predicted distributions are perfect, then it is known that this problem can be solved optimally by the Gittins index *** goal of our work is to design a scheduling policy that is robust in the sense that it produces nearly optimal schedules even if there are modest discrepancies between the predicted distributions and the underlying real distributions. Our main contributions are: - We show that the standard Gittins index policy is not robust in this sense. If the true distributions are perturbed by even an arbitrarily small amount, then running the Gittins index policy using the perturbed distributions can lead to an unbounded increase in mean completion time. - We explain how to modify the Gittins index policy to make it robust, that is, to produce nearly optimal schedules, where the approximation depends on a new measure of error between the true and predicted distributions that we define. Looking forward, the approach we develop here can be applied more broadly to many other stochastic optimization problems to better understand the impact of mispredictions, and lead to the development of new algorithms that are robust against such mispredictions.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Fairness and Robustness in Machine Unlearning

arXiv

引用

arXiv 2025年

作者： Tran, Khoa Woo, Simon S. Department of Computer Science and Engineering Sungkyunkwan University Suwon Korea Republic of

Machine unlearning poses the challenge of "how to eliminate the influence of specific data from a pretrained model" in regard to privacy concerns. While prior research on approximated unlearning has demonstrated accuracy and efficiency in time complexity, we claim that it falls short of achieving exact unlearning, and we are the first to focus on fairness and robustness in machine unlearning algorithms. Our study presents fairness Conjectures for a well-trained model, based on the variance-bias trade-off characteristic, and considers their relevance to robustness. Our Conjectures are supported by experiments conducted on the two most widely used model architectures—ResNet and ViT—demonstrating the correlation between fairness and robustness: the higher fairness-gap is, the more the model is sensitive and vulnerable. In addition, our experiments demonstrate the vulnerability of current state-of-the-art approximated unlearning algorithms to adversarial attacks, where their unlearned models suffer a significant drop in accuracy compared to the exact-unlearned models. We claim that our fairness-gap measurement and robustness metric should be used to evaluate the unlearning algorithm. Furthermore, we demonstrate that unlearning in the intermediate and last layers is sufficient and cost-effective for time and memory complexity. © 2025, CC BY-NC-SA.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Decentralized Optimal Control for Linear Stochastic Systems with Control Signals subject to Unknown Noises

Decentralized Optimal Control for Linear Stochastic Systems ...

引用

International Conference on Control and Automation (ICCA)

作者： Zhaorong Zhang Juanjuan Xu Minyue Fu Xun Li School of Computer Science and Technology Shandong University Qingdao China School of Control Science and Engineering Shandong University Jinan China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Department of Applied Mathematics the Hong Kong Polytechnic University Hong Kong SAR China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

Decentralized strategies have been extensively applied to LQ optimal control problems, whereas, stochastic systems with unknown random parameters have not been comprehensively studied. In this paper, we consider a class of stochastic systems with a decentralized configuration consisting of multiple controllers which have access to Gaussian noises with unknown statistical information. The stabilizing and optimal control strategies are acquired by designing a novel stochastic approximation algorithm recursively evaluating the zero points of certain matrix equations, which is confirmed to be equivalent with solving the corresponding Riccati equations. The proof of convergence and boundness of the proposed algorithm is presented.

关键词： Q-learning Automation Stochastic systems Gaussian noise Riccati equations Optimal control approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Exploiting Storage for Computing: Computation Reuse in Collaborative Edge Computing

Exploiting Storage for Computing: Computation Reuse in Colla...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Xingqiu He Chaoqun You Tony Q. S. Quek Fudan University Singapore University of Technology and Design

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Collaborative Edge Computing (CEC) is a new edge computing paradigm that enables neighboring edge servers to share computational resources with each other. Although CEC can enhance the utilization of computational resources, it still suffers from resource waste. The primary reason is that end-users from the same area are likely to offload similar tasks to edge servers, thereby leading to duplicate computations. To improve system efficiency, the computation results of previously executed tasks can be cached and then reused by subsequent tasks. However, most existing computation reuse algorithms only consider one edge server, which significantly limits the effectiveness of computation reuse. To address this issue, this paper applies computation reuse in CEC networks to exploit the collaboration among edge servers. We formulate an optimization problem that aims to minimize the overall task response time and decompose it into a caching subproblem and a scheduling subproblem. By analyzing the properties of optimal solutions, we show that the optimal caching decisions can be efficiently searched using the bisection method. For the scheduling subproblem, we utilize projected gradient descent and backtracking to find a local minimum. Numerical results show that our algorithm significantly reduces the response time in various situations.

关键词： Processor scheduling System performance Collaboration approximation algorithms Computational efficiency Servers Time factors

来源：评论

学校读者我要写书评

暂无评论

On Approximate Fully-Dynamic Matching and Online Matrix-Vector Multiplication

On Approximate Fully-Dynamic Matching and Online Matrix-Vect...

引用

Annual IEEE Symposium on Foundations of Computer Science

作者： Yang P. Liu School of Mathematics Institute for Advanced Study Princeton USA

ISBN: (数字)9798331516741

ISBN: (纸本)9798331516758

We study connections between the problem of fully dynamic $(1-\epsilon)$ -approximate maximum bipartite matching, and the dual $(1+\epsilon)$ -approximate vertex cover problem, with the online matrix-vector (OMv) conjecture which has recently been used in several fine-grained hardness reductions. We prove that there is an online algorithm that maintains a $(1+\epsilon)$ -approximate vertex cover in amortized $n^{1-c}\epsilon^{-C}$ time for constants $c, C > 0$ for fully dynamic updates if and only if the OMv conjecture is false. Similarly, we prove that there is an online algorithm that maintains a $(1-\epsilon)$ -approximate maximum matching in amortized $n^{1-c}\epsilon^{-C}$ time if and only if there is a nontrivial algorithm for another dynamic problem, which we call dynamic approximate OMv, that has seemingly no matching structure. This provides some evidence against achieving amortized sublinear update times for approximate fully dynamic matching and vertex cover. Leveraging these connections, we obtain faster algorithms for approximate fully dynamic matching in both the online and offline settings. We give a randomized algorithm that with high probability maintains a $(1-\epsilon)$ -approximate bipartite matching and $(1+\epsilon)$ -approximate vertex cover in fully dynamic graphs, in amortized $O(\epsilon^{-O(1)}\frac{n}{2^{\Omega}(\sqrt{\log n})})$ up-date time. This improves over the previous fastest runtimes of $O(n/(\log^{*}n)^{\Omega(1)})$ due to Assadi-Behnezhad-Khanna-Li [STOC 2023], and $O_{\epsilon}(n^{1-\Omega_{\epsilon}(1)})$ due to Bhattacharya-Kiss-Saranurak [FOCS 2023] for small $\epsilon$ . Our algorithm leverages fast algorithms for OMv due to Larsen and Williams [SODA 2017]. We give a randomized offline algorithm for (1 - $\epsilon)$ -approximate maximum matching with amortized runtime $O(n^{.58}\epsilon^{-O(1)})$ by using fast matrix multi-plication, significantly improving over the runtim

关键词： Computer science Runtime Heuristic algorithms approximation algorithms Mirrors

来源：评论

学校读者我要写书评

暂无评论

Towards Communication-Efficient Federated Learning Through Particle Swarm Optimization and Knowledge Distillation

Towards Communication-Efficient Federated Learning Through P...

引用

IEEE Annual International Computer Software and Applications Conference (COMPSAC)

作者： Saika Zaman Sajedul Talukder Md Zarif Hossain Sai Mani Teja Puppala Ahmed Imteaj School of Computing Southern Illinois University Carbondale IL

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

The widespread popularity of Federated Learning (FL) has led researchers to delve into its various facets, primarily focusing on personalization, fair resource allocation, privacy, and global optimization, with less attention puts towards the crucial aspect of ensuring efficient and cost-optimized communication between the FL server and its agents. A major challenge in achieving successful model training and inference on distributed edge devices lies in optimizing communication costs amid resource constraints, such as limited bandwidth, and selecting efficient agents. In resource-limited FL scenarios, where agents often rely on unstable networks, the transmission of large model weights can substantially degrade model accuracy and increase communication latency between the FL server and agents. Addressing this challenge, we propose a novel strategy that integrates a knowledge distillation technique with a Particle Swarm Optimization (PSO)-based FL method. This approach focuses on transmitting model scores instead of weights, significantly reducing communication overhead and enhancing model accuracy in unstable environments. Our method, with potential applications in smart city services and industrial IoT, marks a significant step forward in reducing network communication costs and mitigating accuracy loss, thereby optimizing the communication efficiency between the FL server and its agents.

关键词： Adaptation models Accuracy Costs Federated learning Computational modeling Software algorithms approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

An Efficient Low-Rank Sparse Decomposition Method for Moving Object Detection

An Efficient Low-Rank Sparse Decomposition Method for Moving...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Hui Zhu Jin Luo Hu Zhang School of Mathematics and Statistics Xidian University Xi’an China School of Automation Central South University Changsha China College of Computer Science and Engineering Changsha University Changsha China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

Low-rank sparse decomposition (LRSD) based methods are powerful tools for moving object detection. However, the existing low-rank models have high computational complexity due to the high-dimensional video data and the computation of singular value decomposition (SVD) of the optimisation model. Aiming at this problem, a full variational low-rank sparse decomposition method for efficient detection of moving targets is proposed with the theorem that the CUR decomposition can approximate the low-rank matrices well. It significantly improves the computational efficiency compared with existing algorithms. The method achieved such acceleration by using the CUR decomposition when updating the low-rank components, which allows us to obtain an accurate low-rank approximation through only three small submatrices. As a result, it is only necessary to compute the SVD of the small matrices at each iteration throughout the algorithm, which significantly improves the detection efficiency by avoiding costly computations on the full matrices. Experiments show that the method has advantages in both detection accuracy and efficiency.

关键词： Accuracy TV Heuristic algorithms Object detection approximation algorithms Computational efficiency Sparse matrices Matrix decomposition Computational complexity Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Routing and Spectrum Allocation in Broadband Quantum Entanglement Distribution

arXiv

引用

arXiv 2024年

作者： Bali, Rohan Tittelbaugh, Ashley N. Jenkins, Shelbi L. Agrawal, Anuj Horgan, Jerry Ruffini, Marco Kilper, Daniel C. Bash, Boulat A. Department of Electrical and Computer Engineering Department University of Arizona TucsonAZ United States School of Computer Science and Statistics CONNECT Center Trinity College Dublin Dublin Ireland Electronic and Electrical Engineering Department CONNECT Centre Trinity College Dublin Dublin Ireland

We investigate resource allocation for quantum entanglement distribution over an optical network. We characterize and model a network architecture that employs a single broadband quasi-deterministic time-frequency heralded Einstein-Podolsky-Rosen (EPR) pair source, and develop a routing and spectrum allocation scheme for distributing entangled photon pairs over such a network. As our setting allows separately solving the routing and spectrum allocation problems, we first find an optimal polynomial-time routing algorithm. We then employ max-min fairness criterion for spectrum allocation, which presents an NP-hard problem. Thus, we focus on approximately-optimal schemes. We compare their performance by evaluating the max-min and median number of EPR-pair rates assigned by them, and the associated Jain index. We identify two polynomial-time approximation algorithms that perform well, or better than others under these metrics. We also investigate scalability by analyzing how the network size and connectivity affect performance using Watts-Strogatz random graphs. We find that a spectrum allocation approach that achieves higher minimum EPR-pair rate can perform significantly worse when the median EPR-pair rate, Jain index, and computational resources are considered. Additionally, we evaluate the effect of the source node placement on the performance. © 2024, CC BY.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot Active Graph Exploration with Reduced Pose-SLAM Uncertainty via Submodular Optimization

Multi-Robot Active Graph Exploration with Reduced Pose-SLAM ...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Ruofei Bai Shenghai Yuan Hongliang Guo Pengyu Yin Wei-Yun Yau Lihua Xie School of Electrical and Electronic Engineering Nanyang Technological University Singapore Institute for Infocomm Research (I2R) Agency for Science Technology and Research (A*STAR) Singapore

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper considers the multi-robot active graph exploration problem, where robots need to collaboratively cover a graph environment while maintaining reliable pose estimation in collaborative Simultaneous Localization and Mapping (SLAM). Considering both objectives presents challenges for multi-robot pathfinding, as it involves the expensive covariance propagation for SLAM uncertainty evaluation, especially when considering various combinations of robots’ paths. To reduce the computational complexity, we propose an efficient two-stage strategy where exploration paths are first generated for quick coverage, and then enhanced by adding informative loop-closing actions along the paths for reliable pose estimation. We formulate the latter problem as a non-monotone submodular maximization problem by relating SLAM uncertainty with pose graph topology, which (1) facilitates a more efficient evaluation of SLAM uncertainty than covariance inference, and (2) allows the employment of approximation algorithms in submodular optimization to provide suboptimality guarantees. We further introduce ordering heuristics to improve the objective values while preserving the optimality bound. Simulation experiments over randomly generated graph environments verify the effectiveness of our methods to achieve quick coverage and enhanced pose graph reliability, and benchmark the performance of the approximation algorithms and the greedy-based algorithm in the loop edge selection problem. Our implementations will be open-source at https://***/bairuofei/CGE.

关键词： Simultaneous localization and mapping Uncertainty Pose estimation Employment approximation algorithms Inference algorithms Topology Reliability Optimization Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

A 28nm 343.5fps/W Vision Transformer Accelerator with Integer-Only Quantized Attention Block

A 28nm 343.5fps/W Vision Transformer Accelerator with Intege...

引用

IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Cheng-Chen Lin Wei Lu Po-Tsang Huang Hung-Ming Chen International College of Semiconductor Technology National Yang Ming Chiao Tung University Taiwan Institute of Electronics National Yang Ming Chiao Tung University Taiwan

ISBN: (数字)9798350383638

ISBN: (纸本)9798350383645

Vision Transformer (ViT) has achieved state-of-the-art performance on various computer vision tasks. For the mobile/edge device, the energy efficiency is the most important issue. However, ViT requires huge computation and storage, which makes it difficult to be deployed on mobile/edge device. In this work, we focus on algorithm level and hardware level to improve efficiency of ViT inference. At algorithm level, we proposed energy efficient ViT model by adopting 4bit Quantization and Low-Rank approximation to convert all the non-linear functions with floating point (FP) values in Multi-Head Attention (MHA) to linear function with integer (INT) values, to decrease the overhead caused by computation and storage. There are less accuracy drop compare with full-precision (<1.5%). At hardware level, we design an energy efficient row-based pipelined ViT accelerator for on-device inference. The proposed accelerator is consisted of integer-only quantizer, integer MACs PE array used for executing quantization and matrix operations, and approximated linear block adopted for executing low-rank approximation. As we know, in the research of ViT, this is the first accelerator uses 4-bits quantization and designs quantizer to operate integer-only quantization for on-device inference. This work can achieve energy efficiency of 343.5 fps/W and improve up to 8x energy efficiency compare to state-of-art works.

关键词： Quantization (signal) Accuracy Computational modeling Transformers approximation algorithms Taylor series Energy efficiency

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：