检索结果-内蒙古大学图书馆

Self-Healing First-Order Distributed Optimization with Packet Loss

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Donato Ridgley, israel L. Freeman, Randy A. Lynch, Kevin M. Northwestern University EvanstonIL60208 United States Department of Electrical & Computer Engineering Department of Mechanical Engineering Northwestern Institute on Complex Systems United States Center for Robotics and Biosystems United States

We describe SH-SVL, a parameterized family of first-order distributed optimization algorithms that enable a network of agents to collaboratively calculate a decision variable that minimizes the sum of cost functions at each agent. These algorithms are self-healing in that their convergence to the correct optimizer can be guaranteed even if they are initialized randomly, agents join or leave the network, or local cost functions change. We also present simulation evidence that our algorithms are self-healing in the case of dropped communication packets. Our algorithms are the first single-Laplacian methods for distributed convex optimization to exhibit all of these characteristics. We achieve self-healing by sacrificing internal stability, a fundamental trade-off for single-Laplacian methods. © 2023, CC BY-SA.

关键词： Cost functions

Unveiling Group-Specific Distributed Concept Drift: A Fairness Imperative in Federated Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Salazar, Teresa Gama, João Araujo, Helder Abreu, Pedro Henriques The Centre for Informatics and Systems Department of Informatics Engineering University of Coimbra Coimbra3030-790 Portugal INESC TEC The Faculty of Economy University of Porto Porto4200-465 Portugal The Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Coimbra3004-531 Portugal

In the evolving field of machine learning, ensuring fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time while another does not, leading to a decrease in fairness even if accuracy remains fairly stable. Within the framework of Federated Learning, where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the realm of fairness. Additionally, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift which uses a multi-model approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine *** Codes 68T01 © 2024, CC BY.

关键词： Machine learning

Verifying Nonlinear Neural Feedback systems using Polyhedral Enclosures

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Akinwande, Samuel I. Sidrane, Chelsea Kochenderfer, Mykel J. Barrett, Clark Department of Aeronautical and Astronautical Engineering Stanford University StanfordCA94305 United States Department of Computer Science Stanford University StanfordCA94305 United States Division of Robotics Perception and Learning Intelligent Systems Department School of Electrical Engineering & Computer Science KTH Royal Institute of Technology Stockholm Sweden

As dynamical systems equipped with neural network controllers (neural feedback systems) become increasingly prevalent, it is critical to develop methods to ensure their safe operation. Verifying safety requires extending control theoretic analysis methods to these systems. Although existing techniques can efficiently handle linear neural feedback systems, relatively few scalable methods address the nonlinear case. We propose a novel algorithm for forward reachability analysis of nonlinear neural feedback systems. The approach leverages the structure of the nonlinear transition functions of the systems to compute tight polyhedral enclosures (i.e., abstractions). These enclosures, combined with the neural controller, are then encoded as a mixed-integer linear program (MILP). Optimizing this MILP yields a sound over-approximation of the forward-reachable set. We evaluate our algorithm on representative benchmarks and demonstrate an order of magnitude improvement over the current state of the art. Copyright © 2025, The Authors. All rights reserved.

关键词： Mixed-integer linear programming

An Isomerism Learning Model to Solve Time-Varying Problems Through Intelligent Collaboration

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1772-1774页

作者： Zhihao Hao Guancheng Wang Bob Zhang Leyuan Fang Haisheng Li the Department of Computer and Information Science University of MacaoMacao 999078China the School of Data Science the Chinese University of Hong KongShenzhen 518172 Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen 518000 China Industrial Control Systems Cyber Emergency Response Team Beijing 100040China IEEE the College of Electrical and Information Engineering Hunan UniversityChangsha 410082 the Peng Cheng Laboratory Shenzhen 518000China the Beijing Key Laboratory of Big Data Technology for Food Safety Beijing Technology and Business UniversityBeijing 100048 the School of Computer Science and Engineering Beijing Technology and Business UniversityBeijing 100048China

Dear Editor,This letter deals with a solution for time-varying problems using an intelligent computational(IC)algorithm driven by a novel decentralized machine learning approach called isomerism *** order to meet the challenges of the model’s privacy and security brought by traditional centralized learning models,a private permissioned blockchain is utilized to decentralize the model in order to achieve an effective coordination,thereby ensuring the credibility of the overall model without exposing the specific parameters and solution process.

关键词： ism thereby letter

Revisiting the K-nn algorithm for obstetric image segmentation

学校读者我要写书评

暂无评论

International Journal of Hybrid Intelligent systems 2021年第1-2期17卷 1-13页

作者： Salgado, P. Azevedo Perdicoúlis, T.-P. CITAB-Department de Engenharias Ect Utad Quinta de Prados Vila Real Portugal Department of Electrical and Computer Engineering Ect Utad of Institute of Systems and Robotics University of Coimbra Coimbra Portugal

Medical image techniques are used to examine and determine the well-being of the foetus during pregnancy. Digital image processing (DIP) is essential to extract valuable information embedded in most biomedical signals. Afterwords, intelligent segmentation methods, based on classifier algorithms, must be applied to identify structures and relevant features from previous data. The success of both is essential for helping doctors to identify adverse health conditions from the medical images. To obtain easy and reliable DIP methods for foetus images in real-time, at different gestational ages, aware pre-processing needs to be applied to the images. Thence, some data features are extracted that are meant to be used as input to the segmentation algorithms presented in this work. Due to the high dimension of the problems in question, assemblage of the data is also desired. The segmentation of the images is done by revisiting the K-nn algorithm that is a conventional nonparametric classifier. Besides its simplicity, its power to accomplish high classification results in medical applications has been demonstrated. In this work two versions of this algorithm are presented (i) an enhancement of the standard version by aggregating the data apriori and (ii) an iterative version of the same method where the training set (TS) is not static. The procedure is demonstrated in two experiments, where two images of different technologies were selected: a magnetic resonance image and an ultrasound image, respectively. The results were assessed by comparison with the K-means clustering algorithm, a well-known and robust method for this type of task. Both described versions showed results close to 100% matching with the ones obtained by the validation method, although the iterative version displays much higher reliability in the classification. © 2021 - IOS Press. All rights reserved.

关键词： Feature extraction image segmentation K-nn algorithm magnetic resonance image ultrasound image

Harvesting Curvatures for Communication-Efficient Distributed Optimization

学校读者我要写书评

暂无评论

Harvesting Curvatures for Communication-Efficient Distribute...

Asilomar Conference on Signals, systems & computers

作者： Diogo Cardoso Boyue Li Yuejie Chi João Xavier Department of Electrical and Computer Engineering Carnegie Mellon University USA Institute for Systems and Robotics IST-University of Lisbon Portugal

This paper considers the design of distributed optimization algorithms in the server-client setting, with the goal of achieving better communication efficiency, a crucial desiderata in modern distributed machine learning applications. One popular approach to reduce communication is to impose more computation between communication rounds, by letting each client optimize an approximation of the global objective function-constructed using the local objective function and aggregated history information-and exchange the updates with the parameter server for global consensus. In particular, judiciously incorporating second-order information in the local approximation often leads to better communication efficiency when the problem is ill-conditioned. However, existing methods construct the second-order correction term in an isotropic manner, without taking into account the curvature information of the global objective function accumulated over the course of the algorithm. This paper proposes a novel algorithm that refines this idea by constructing a second-order correction term using a BFGS-style update formula, where the kernel matrix is updated recursively using only history gradients to harvest curvature information for accelerating convergence. Numerical experiments demonstrate improved communication efficiency over competitive baseline algorithms on both synthetic and real datasets.

关键词： Machine learning algorithms Memory management Machine learning Approximation algorithms Linear programming Servers History

Enhancing Precision Agriculture Through Human-in-the-Loop Planning and Control

学校读者我要写书评

暂无评论

Enhancing Precision Agriculture Through Human-in-the-Loop Pl...

IEEE International Conference on Automation Science and engineering (CASE)

作者： Shankar A. Deka Sujet Phodapol Andreu Matoses Gimenez Victor Nan Fernandez-Ayala Rufus Wong Pian Yu Xiao Tan Dimos V. Dimarogonas Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Division of Decision and Control Systems School of EECS Royal Institute of Technology (KTH) Stockholm Sweden Department of Cognitive Robotics Faculty of Mechanical Engineering TU Delft Delft Netherlands Department of Computer Science University of Oxford Oxford UK

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

In this paper, we introduce a ROS based framework designed for the planning and control of robotic systems within the context of precision agriculture, with an emphasis on human-in-the-loop capabilities. Utilizing Linear Temporal Logic to articulate complex task specifications, our algorithm creates high-level robotic plans that are not only correct by design but also adaptable in real time by human operators. This dual-focus approach ensures that while humans have the flexibility to modify the high-level plan on-the-fly or even take over low-level control of the robots, the system inherently safeguards against any human actions that could potentially breach the predefined task specifications. We demonstrate our algorithm within the dynamic and challenging environment of a real vineyard, where the collaboration between human workers and robots is critical for tasks such as harvesting and pruning, and show the practical applicability and robustness of our software. This work marks a pioneering application of formal methods to complex, real-world agricultural environments.

关键词： Precision agriculture Heuristic algorithms Software algorithms Robustness Human in the loop Software Real-time systems Planning Robots Multi-agent systems

Approaching Metaheuristic Deep Learning Combos for Automated Data Mining

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Assunção, Gustavo Menezes, Paulo Institute of Systems and Robotics University of Coimbra R. Silvio Lima Coimbra3030-194 Portugal Department of Electrical and Computer Engineering University of Coimbra R. Silvio Lima Coimbra3030-194 Portugal

Lack of data on which to perform experimentation is a recurring issue in many areas of research, particularly in machine learning. The inability of most automated data mining techniques to be generalized to all types of data is inherently related with their dependency on those types which deems them ineffective against anything slightly different. Meta-heuristics are algorithms which attempt to optimize some solution independently of the type of data used, whilst classifiers or neural networks focus on feature extrapolation and dimensionality reduction to fit some model onto data arranged in a particular way. These two algorithmic fields encompass a group of characteristics which when combined are seemingly capable of achieving data mining regardless of how it is arranged. To this end, this work proposes a means of combining meta-heuristic methods with conventional classifiers and neural networks in order to perform automated data mining. Experiments on the MNIST dataset for handwritten digit recognition were performed and it was empirically observed that using a ground truth labeled dataset’s validation accuracy is inadequate for correcting labels of other previously unseen data instances. © 2024, CC BY.

关键词： Adversarial machine learning

Communication-efficient Vertical Federated Learning via Compressed Error Feedback

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Valdeira, Pedro Xavier, João Soares, Cláudia Chi, Yuejie CMU IST United States IST NOVA CMU United States Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Systems and Robotics Instituto Superior Técnico Portugal Department of Computer Science NOVA School of Science and Technology

Communication overhead is a known bottleneck in federated learning (FL). To address this, lossy compression is commonly used on the information communicated between the server and clients during training. In horizontal FL, where each client holds a subset of the samples, such communication-compressed training methods have recently seen significant progress. However, in their vertical FL counterparts, where each client holds a subset of the features, our understanding remains limited. To address this, we propose an error feedback compressed vertical federated learning (EF-VFL) method to train split neural networks. In contrast to previous communication-compressed methods for vertical FL, EF-VFL does not require a vanishing compression error for the gradient norm to converge to zero for smooth nonconvex problems. By leveraging error feedback, our method can achieve a O(1/T) convergence rate for a sufficiently large batch size, improving over the state-of-the-art O(1/√T) rate under O(1/√T) compression error, and matching the rate of uncompressed methods. Further, when the objective function satisfies the Polyak-Lojasiewicz inequality, our method converges linearly. In addition to improving convergence, our method also supports the use of private labels. Numerical experiments show that EF-VFL significantly improves over the prior art, confirming our theoretical results. The code for this work can be found at https://***/Valdeira/EF-VFL. © 2024, CC BY.

关键词： Federated learning