In this paper, we consider the binary classification problem via distributed Support-Vector-Machines (SVM), where the idea is to train a network of agents, with limited share of data, to cooperatively learn the SVM classifier for the global database. Agents only share processed information regarding the classifier parameters and the gradient of the local loss functions instead of their raw data. In contrast to the existing work, we propose a continuous-time algorithm that incorporates network topology changes in discrete jumps. This hybrid nature allows us to remove chattering that arises because of the discretization of the underlying CT process. We show that the proposed algorithm converges to the SVM classifier over time-varying weight balanced directed graphs by using arguments from the matrix perturbation theory.
This paper deals with linear algebraic equations where the global coefficient matrix and constant vector are given respectively, by the summation of the coefficient matrices and constant vectors of the individual agents. Our approach is based on reformulating the original problem as an unconstrained optimization. Based on this exact reformulation, we first provide a gradient-based, centralized algorithm which serves as a reference for the ensuing design of distributed algorithms. We propose two sets of exponentially stable continuous-time distributed algorithms that do not require the individu…
This work is concerned with the problem of distributed resource allocation in continuous-time setting but with discrete-time communication over infinitely jointly connected and balanced digraphs. We provide a passivity-based perspective for the continuous-time algorithm, based on which an intermittent communication scheme is developed. Particularly, a periodic communication scheme is first derived through analyzing the passivity degradation over output sampling of the distributed dynamics at each node. Then, an asynchronous distributed event-triggered scheme is further developed. The sampled-b…
North Carolina State University（北卡罗来纳州立大学）；Oklahoma State University（俄克拉荷马州立大学）；DEVCOM U.S. Army Research Laboratory（美国陆军作战能力发展司令部陆军研究实验室）
Existing distributed cooperative multi-agent reinforcement learning (MARL) frameworks usually assume undirected coordination graphs and communication graphs while estimating a global reward via consensus algorithms for policy evaluation. Such a framework may induce expensive communication costs and exhibit poor scalability due to requirement of global consensus. In this work, we study MARLs with directed coordination graphs, and propose a distributed RL algorithm where the local policy evaluations are based on local value functions. The local value function of each agent is obtained by local c…
Fully distributed consensus control for stochastic multi-agent systems under undirected and directed topologies
China University of Geosciences（中国地质大学）；Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems（复杂系统先进控制与智能自动化湖北省重点实验室）
Designing Distributed Fixed-Time Consensus Protocols for Linear Multi-Agent Systems Over Directed Graphs
School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）；Department of Electronic Engineering, City University of Hong Kong（香港城市大学电子工程系）
In this paper, we study the problem of consensus-based distributed optimization where a network of agents, abstracted as a directed graph, aims to minimize the sum of all agents' cost functions collaboratively. In existing distributed optimization approaches (Push-Pull/AB) for directed graphs, all agents exchange their states with neighbors to achieve the optimal solution with a constant stepsize, which may lead to the disclosure of sensitive and private information. For privacy preservation, we propose a novel state-decomposition based gradient tracking approach (SD-Push-Pull) for distributed…
In this note, a novel observer-based output feedback control approach is proposed to address the distributed optimal output consensus problem of uncertain nonlinear multi-agent systems in the normal form over unbalanced directed graphs. The main challenges of the concerned problem lie in unbalanced directed graphs and nonlinearities of multi-agent systems with their agent states not available for feedback control. Based on a two-layer controller structure, a distributed optimal coordinator is first designed to convert the considered problem into a reference-tracking problem. Then a decentraliz…
This article reports an algorithm for multi-agent distributed optimization problems with a common decision variable, local linear equality and inequality constraints and set constraints with convergence rate guarantees. \textcolor{black}{The algorithm accrues all the benefits of the Alternating Direction Method of Multipliers (ADMM) approach}. It also overcomes the limitations of existing methods on convex optimization problems with linear inequality, equality and set constraints by allowing directed communication topologies. Moreover, the algorithm can be synthesized distributively. The devel…
Motivated by the needs of resiliency, scalability, and plug-and-play operation, distributed decision-making is becoming increasingly prevalent. The problem of achieving consensus in a multi-agent system is at the core of distributed decision-making. In this article, we study the problem of achieving average consensus over a directed multi-agent network when the communication links are corrupted with noise. We propose an algorithm where each agent updates its estimates based on the local mixing of information and adds its weighted noise-free initial information to its updates during every itera…
In this paper, we study the leaderless consensus problem for multiple Lagrangian systems in the presence of parametric uncertainties and external disturbances under directed graphs. For achieving asymptotic behavior, a robust continuous term with adaptive varying gains is added to alleviate the effects of the external disturbances with unknown bounds. In the case of a fixed directed graph, by introducing an integrate term in the auxiliary variable design, the final consensus equilibrium can be explicitly derived. We show that the agents achieve weighted average consensus, where the final equil…
Differentially Private Gradient-Tracking-Based Distributed Stochastic Optimization over Directed Graphs
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；School of Mathematical Sciences, University of Chinese Academy of Sciences（中国科学院大学数学科学学院）；School of Automation and Electrical Engineering, University of Science and Technology Beijing（北京科技大学自动化与电气工程学院）；Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education（教育部工业过程知识自动化重点实验室）；School of Automation and Electrical Engineering, Zhongyuan University of Technology（中原工学院自动化与电气工程学院）
This paper investigates the distributed optimal output consensus problem of second-order uncertain nonlinear multi-agent systems over weight-unbalanced directed networks. Under the standard assumption that local cost functions are strongly convex with globally Lipschitz gradients, a novel distributed dynamic state feedback controller is developed such that the outputs of all the agents reach the optimal solution to minimize the global cost function which is the sum of all the local cost functions. The controller design is based on a two-layer strategy, where a distributed optimal coordinator a…
Fast Distributed Optimization over Directed Graphs under Malicious Attacks using Trust
School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；Faculty of Engineering, Bar-Ilan University（巴伊兰大学工程学院）；School of Electrical, Computer and Energy Engineering, Arizona State University（亚利桑那州立大学电气、计算机与能源工程学院）
Network structure plays a critical role in functionality and performance of network systems. This paper examines structural adaptivity of diffusively coupled, directed multi-agent networks that are subject to diffusion performance. Inspired by the observation that the link redundancy in a network may degrade its diffusion performance, a distributed data-driven neighbor selection framework is proposed to adaptively adjust the network structure for improving the diffusion performance of exogenous influence over the network. Specifically, each agent is allowed to interact with only a specific sub…
In this article, we propose a new approach, optimize then agree for minimizing a sum $ f = \sum_{i=1}^n f_i(x)$ of convex objective functions over a directed graph. The optimize then agree approach decouples the optimization step and the consensus step in a distributed optimization framework. The key motivation for optimize then agree is to guarantee that the disagreement between the estimates of the agents during every iteration of the distributed optimization algorithm remains under any apriori specified tolerance; existing algorithms do not provide such a guarantee which is required in many…
Max-Consensus with Deterministic Convergence in Directed Graphs with Unreliable Communication Links
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；University of Cyprus（塞浦路斯大学）；Aalto University（阿尔托大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）
Universidad Nacional de Colombia（哥伦比亚国立大学）；Lehigh University（理海大学）；Universidad Santo Tomas（圣托马斯大学）；Bethune Cookman University（贝休恩-库克曼大学）
We develop an event-triggered control strategy for a weighted-unbalanced directed homogeneous robot network to reach a dynamic consensus in this work. We present some guarantees for synchronizing a robot network when all robots have access to the reference and when a limited number of robots have access. The proposed event-triggered control can reduce and avoid the periodic updating of the signals. Unlike some current control methods, we prove stability by making use of a logarithmic norm, which extends the possibilities of the control law to be applied to a wide range of directed graphs, in c…
