IEEE Transactions on Automatic Control

最新文章

• Quantization Enabled Privacy Protection in Decentralized Stochastic Optimization AI翻译
  作者：Wang, Yongqiang; Basar, Tamer
  作者单位：Clemson University; University of Illinois System; University of Illinois Urbana-Champaign
  摘要：By enabling multiple agents to cooperatively solve a global optimization problem in the absence of a central coordinator, decentralized stochastic optimization is gaining increasing attention in areas as diverse as machine learning, control, and sensor networks. Since the associated data usually contain sensitive information, such as user locations and personal identities, privacy protection has emerged as a crucial need in the implementation of decentralized stochastic optimization. In this a...
• Identification of Diffusively Coupled Linear Networks Through Structured Polynomial Models AI翻译
  作者：Kivits, E. M. M.; van den Hof, Paul M. J.
  作者单位：Eindhoven University of Technology
  摘要：Physical dynamic networks most commonly consist of interconnections of physical components that can be described by diffusive couplings. These diffusive couplings imply that the cause-effect relationships in the interconnections are symmetric, and therefore, physical dynamic networks can be represented by undirected graphs. This article shows how prediction error identification methods developed for linear time-invariant systems in polynomial form can be configured to consistently identify the...
• Learning to Act Safely With Limited Exposure and Almost Sure Certainty AI翻译
  作者：Castellano, Agustin; Min, Hancheng; Bazerque, Juan Andres; Mallada, Enrique
  作者单位：Johns Hopkins University; Pennsylvania Commonwealth System of Higher Education (PCSHE); University of Pittsburgh
  摘要：This article puts forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an unbounded number of exploratory trials. This is indeed possible, provided that one is willing to navigate tradeoffs between optimality, level of exposure to unsafe events, and the maximum detection time of unsafe actions. We illustrate this concept in two complementary settings. We first focus on the canonical multiarmed...
• Data-Driven Inference on Optimal Input-Output Properties of Polynomial Systems With Focus on Nonlinearity Measures AI翻译
  作者：Martin, Tim; Allgoewer, Frank
  作者单位：University of Stuttgart
  摘要：In the context of dynamical systems, nonlinearity measures quantify the strength of nonlinearity by means of the distance of their input-output behavior to a set of linear input-output mappings. In this article, we establish a framework to determine nonlinearity measures and other optimal input-output properties for nonlinear polynomial systems without explicitly identifying a model but from a finite number of input-state measurements, which are subject to noise. To this end, we deduce from da...
• Finite-Time Convergence Rates of Decentralized Stochastic Approximation With Applications in Multi-Agent and Multi-Task Learning AI翻译
  作者：Zeng, Sihan; Doan, Thinh T.; Romberg, Justin
  作者单位：University System of Georgia; Georgia Institute of Technology; Virginia Polytechnic Institute & State University
  摘要：In this article, we study a decentralized variant of stochastic approximation (SA), a data-driven approach for finding the root of an operator under noisy measurements. A network of agents, each with its own operator and data observations, cooperatively find the fixed point of the aggregate operator over a decentralized communication graph. Our main contribution is to provide a finite-time analysis of this decentralized SA method when the data observed at each agent are sampled from a Markov p...
• Policy Optimization for Markovian Jump Linear Quadratic Control: Gradient Method and Global Convergence AI翻译
  作者：Jansch-Porto, Joao Paulo; Hu, Bin; Dullerud, Geir E.
  作者单位：University of Illinois System; University of Illinois Urbana-Champaign; University of Illinois System; University of Illinois Urbana-Champaign
  摘要：Recently, policy optimization has received renewed attention from the control community due to various applications in reinforcement learning tasks. In this article, we investigate the global convergence of the gradient method for quadratic optimal control of discrete-time Markovian jump linear systems (MJLS). First, we study the optimization landscape of direct policy optimization for MJLS, with static-state feedback controllers and quadratic performance costs. Despite the nonconvexity of the...
• About Robustness of Control Systems Embedding an Internal Model AI翻译
  作者：Bin, Michelangelo; Astolfi, Daniele; Marconi, Lorenzo
  作者单位：Imperial College London; Centre National de la Recherche Scientifique (CNRS); CNRS - Institute for Engineering & Systems Sciences (INSIS); Universite Claude Bernard Lyon 1; University of Bologna
  摘要：Robustness is a basic property of any control system. In the context of linear output regulation, it was proved that embedding an internal model of the exogenous signals is necessary and sufficient to achieve tracking of the desired reference signals in spite of external disturbances and parametric uncertainties. This result is commonly known as the internal model principle. A complete extension of such linear result to general nonlinear systems is still an open problem, exacerbated by the lar...
• Projection Scheme and Adaptive Control for Symmetric Matrices With Eigenvalue Bounds AI翻译
  作者：Moghe, Rahul; Akella, Maruthi R.
  作者单位：University of Texas System; University of Texas Austin
  摘要：A projection scheme to handle eigenvalue bounds for adaptive control with uncertain symmetric matrix parameters is introduced. Conventional parameter projection techniques are generally unable to handle explicit eigenvalue bounds. The continuous projection scheme presented here maintains the closed-loop stability properties for adaptive controllers while simultaneously satisfying a priori available eigenvalue bounds of the uncertain symmetric matrix valued parameters. The projection scheme use...
• Transient Growth of Accelerated Optimization Algorithms AI翻译
  作者：Mohammadi, Hesameddin; Samuelson, Samantha; Jovanovic, Mihailo R.
  作者单位：University of Southern California
  摘要：Optimization algorithms are increasingly being used in applications with limited time budgets. In many real-time and embedded scenarios, only a few iterations can be performed and traditional convergence metrics cannot be used to evaluate performance in these nonasymptotic regimes. In this article, we examine the transient behavior of accelerated first-order optimization algorithms. For convex quadratic problems, we employ tools from linear systems theory to show that transient growth arises f...
• Computation of the Distance-Based Bound on Strong Structural Controllability in Networks AI翻译
  作者：Shabbir, Mudassir; Abbas, Waseem; Yazcoglu, A. Yasin; Koutsoukos, Xenofon
  作者单位：Vanderbilt University; University of Texas System; University of Texas Dallas; University of Minnesota System; University of Minnesota Twin Cities
  摘要：In this article, we study the problem of computing a tight lower bound on the dimension of the strong structurally controllable subspace (SSCS) in networks with Laplacian dynamics. The bound is based on a sequence of vectors containing the distances between leaders (nodes with external inputs) and followers (remaining nodes) in the underlying network graph. Such vectors are referred to as the distance-to-leaders vectors. We give exact and approximate algorithms to compute the longest sequences...