5期

最新文章

• 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...
• Finite-Time Identification of Linear Systems: Fundamental Limits and Optimal Algorithms AI翻译
  作者：Jedra, Yassir; Proutiere, Alexandre
  作者单位：Royal Institute of Technology
  摘要：We investigate the linear system identification problem in the so-called fixed budget and fixed confidence settings. In the fixed budget setting, the learner aims at estimating the state transition matrix A from a random system trajectory of fixed length, whereas in the fixed confidence setting, the learner also controls the length of the observed trajectory - she can stop when she believes that enough information has been gathered. For both settings, we analyze the sample complexity in the pr...
• Predictive Control Barrier Functions: Enhanced Safety Mechanisms for Learning-Based Control AI翻译
  作者：Wabersich, Kim P.; Zeilinger, Melanie N.
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich
  摘要：While learning-based control techniques often outperform classical controller designs, safety requirements limit the acceptance of such methods in many applications. Recent developments address this issue through so-called predictive safety filters, which assess if a proposed learning-based control input can lead to constraint violations and modifies it if necessary to ensure safety for all future time steps. The theoretical guarantees of such predictive safety filters rely on the model assump...
• Robust Uncertainty Bounds in Reproducing Kernel Hilbert Spaces: A Convex Optimization Approach AI翻译
  作者：Scharnhorst, Paul; Maddalena, Emilio T.; Jiang, Yuning; Jones, Colin N.
  作者单位：Swiss Center for Electronics & Microtechnology (CSEM); Swiss Federal Institutes of Technology Domain; Ecole Polytechnique Federale de Lausanne
  摘要：The problem of establishing out-of-sample bounds for the values of an unknown ground-truth function is considered. Kernels and their associated Hilbert spaces are the main formalism employed herein, along with an observational model where outputs are corrupted by bounded measurement noise. The noise can originate from any compactly supported distribution, and no independent assumptions are made on the available data. In this setting, we show how computing tight, finite-sample uncertainty bound...
• Recursive Identification of Time-Varying Hammerstein Systems With Matrix Forgetting AI翻译
  作者：Dokoupil, Jakub; Vaclavek, Pavel
  作者单位：Brno University of Technology
  摘要：The real-time estimation of the time-varying Hammerstein system by using a noniterative learning schema is considered and extended to incorporate a matrix forgetting factor. The estimation is cast in a variational-Bayes framework to best emulate the original posterior distribution of the parameters within the set of distributions with feasible moments. The recursive concept we propose approximates the exact posterior comprising undistorted information about the estimated parameters. In many pr...
• Robust Data-Enabled Predictive Control: Tractable Formulations and Performance Guarantees AI翻译
  作者：Huang, Linbin; Zhen, Jianzhe; Lygeros, John; Dorfler, Florian
  作者单位：Swiss Federal Institutes of Technology Domain; ETH Zurich
  摘要：We introduce a general framework for robust data-enabled predictive control (DeePC) for linear time-invariant systems, which enables us to obtain robust and optimal control in a receding-horizon fashion based on inexact input and output data. Robust DeePC solves a min-max optimization problem to compute the optimal control sequence that is resilient to all possible realizations of the uncertainties in data within a prescribed uncertainty set. We present computationally tractable reformulations...
• On Centralized and Distributed Mirror Descent: Convergence Analysis Using Quadratic Constraints AI翻译
  作者：Sun, Youbang; Fazlyab, Mahyar; Shahrampour, Shahin
  作者单位：Northeastern University; Johns Hopkins University
  摘要：Mirror descent (MD) is a powerful first-order optimization technique that subsumes several optimization algorithms including gradient descent (GD). In this work, we leverage quadratic constraints and Lyapunov functions to analyze the stability and characterize the convergence rate of the MD algorithm as well as its distributed variant using semidefinite programming (SDP). For both algorithms, we consider both strongly convex and nonstrongly convex assumptions. For centralized MD and strongly c...
• Formal Verification of Unknown Discrete- and Continuous-Time Systems: A Data-Driven Approach AI翻译
  作者：Nejati, Ameneh; Lavaei, Abolfazl; Jagtap, Pushpak; Soudjani, Sadegh; Zamani, Majid
  作者单位：Technical University of Munich; University of Munich; Newcastle University - UK; Bosch; Indian Institute of Science (IISC) - Bangalore; University of Colorado System; University of Colorado Boulder
  摘要：This article is concerned with a formal verification scheme for both discrete- and continuous-time deterministic systems with unknown mathematical models. The main target is to verify the safety of unknown systems based on the construction of barrier certificates via a set of data collected from trajectories of systems while providing an a-priori guaranteed confidence on the safety. In our proposed framework, we first cast the original safety problem as a robust convex program (RCP). Solving t...
• Model-Based Policy Iterations for Nonlinear Systems via Controlled Hamiltonian Dynamics AI翻译
  作者：Sassano, Mario; Mylvaganam, Thulasi; Astolfi, Alessandro
  作者单位：University of Rome Tor Vergata; Imperial College London; Imperial College London
  摘要：The infinite-horizon optimal control problem for nonlinear systems is studied. In the context of model-based, iterative learning strategies we propose an alternative definition and construction of the temporal difference error arising in policy iteration strategies. In such architectures, the error is computed via the evolution of the Hamiltonian function (or, possibly, of its integral) along the trajectories of the closed-loop system. Herein the temporal difference error is instead obtained v...