Learning the Dynamics of Autonomous Linear Systems From Multiple Trajectories

• URL: http://arxiv.org/abs/2203.12794v1
• Date: Thu, 24 Mar 2022 01:29:53 GMT
• Title: Learning the Dynamics of Autonomous Linear Systems From Multiple Trajectories
• Authors: Lei Xin, George Chiu, Shreyas Sundaram
• Abstract summary: Existing results on learning rate and consistency of autonomous linear system identification rely on observations of steady state behaviors from a single long trajectory. We consider the scenario of learning system dynamics based on multiple short trajectories, where there are no easily observed steady state behaviors. We show that one can adjust the length of the trajectories to achieve a learning rate of $mathcalO(sqrtfraclogNN)$ for strictly stable systems and a learning rate of $mathcalO(frac(logN)dsqr
• Score: 2.2268031040603447
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the problem of learning the dynamics of autonomous linear systems (i.e., systems that are not affected by external control inputs) from observations of multiple trajectories of those systems, with finite sample guarantees. Existing results on learning rate and consistency of autonomous linear system identification rely on observations of steady state behaviors from a single long trajectory, and are not applicable to unstable systems. In contrast, we consider the scenario of learning system dynamics based on multiple short trajectories, where there are no easily observed steady state behaviors. We provide a finite sample analysis, which shows that the dynamics can be learned at a rate $\mathcal{O}(\frac{1}{\sqrt{N}})$ for both stable and unstable systems, where $N$ is the number of trajectories, when the initial state of the system has zero mean (which is a common assumption in the existing literature). We further generalize our result to the case where the initial state has non-zero mean. We show that one can adjust the length of the trajectories to achieve a learning rate of $\mathcal{O}(\sqrt{\frac{\log{N}}{N})}$ for strictly stable systems and a learning rate of $\mathcal{O}(\frac{(\log{N})^d}{\sqrt{N}})$ for marginally stable systems, where $d$ is some constant.

Related papers

• From Spectral Theorem to Statistical Independence with Application to System Identification [11.98319841778396]
  We provide first quantitative handle on decay rate of finite powers of state transition matrix $|Ak|$. It is shown that when a stable dynamical system has only one distinct eigenvalue and discrepancy of $n-1$: $|A|$ has a dependence on $n$, resulting dynamics are inseparable. We show that element-wise error is essentially a variant of well-know Littlewood-Offord problem.
  arXiv  Detail & Related papers  (2023-10-16T15:40:43Z)
• Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations [114.17826109037048]
  Ordinary Differential Equations (ODEs) have recently gained a lot of attention in machine learning. theoretical aspects, e.g., identifiability and properties of statistical estimation are still obscure. This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
  arXiv  Detail & Related papers  (2022-10-12T06:46:38Z)
• Finite Sample Identification of Bilinear Dynamical Systems [29.973598501311233]
  We show how to estimate the unknown bilinear system up to a desired accuracy with high probability. Our sample complexity and statistical error rates are optimal in terms of the trajectory length, the dimensionality of the system and the input size.
  arXiv  Detail & Related papers  (2022-08-29T22:34:22Z)
• Learning from many trajectories [37.265419499679474]
  We study supervised learning from many independent sequences of non-independent co variables. Our setup sits between learning from independent examples and learning from a single auto-correlated sequence. A key upshot is that, in domains where trajectories regularly reset, the error rate eventually behaves as if all of the examples were independent altogether.
  arXiv  Detail & Related papers  (2022-03-31T17:17:08Z)
• Learning Networked Linear Dynamical Systems under Non-white Excitation from a Single Trajectory [0.0]
  We study the problem of learning the underlying graph of interactions/dependencies from observations of the nodal trajectories over a time-interval $T$. We present a regularized non-casual consistent estimator for this problem and analyze its sample complexity over two regimes.
  arXiv  Detail & Related papers  (2021-10-02T17:33:16Z)
• Robust Online Control with Model Misspecification [96.23493624553998]
  We study online control of an unknown nonlinear dynamical system with model misspecification. Our study focuses on robustness, which measures how much deviation from the assumed linear approximation can be tolerated.
  arXiv  Detail & Related papers  (2021-07-16T07:04:35Z)
• Learning Stabilizing Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory [85.29718245299341]
  We study linear controllers under quadratic costs model also known as linear quadratic regulators (LQR) We present two different semi-definite programs (SDP) which results in a controller that stabilizes all systems within an ellipsoid uncertainty set. We propose an efficient data dependent algorithm -- textsceXploration -- that with high probability quickly identifies a stabilizing controller.
  arXiv  Detail & Related papers  (2020-06-19T08:58:57Z)
• Active Learning for Nonlinear System Identification with Guarantees [102.43355665393067]
  We study a class of nonlinear dynamical systems whose state transitions depend linearly on a known feature embedding of state-action pairs. We propose an active learning approach that achieves this by repeating three steps: trajectory planning, trajectory tracking, and re-estimation of the system from all available data. We show that our method estimates nonlinear dynamical systems at a parametric rate, similar to the statistical rate of standard linear regression.
  arXiv  Detail & Related papers  (2020-06-18T04:54:11Z)
• Sparse Identification of Nonlinear Dynamical Systems via Reweighted $\ell_1$-regularized Least Squares [62.997667081978825]
  This work proposes an iterative sparse-regularized regression method to recover governing equations of nonlinear systems from noisy state measurements. The aim of this work is to improve the accuracy and robustness of the method in the presence of state measurement noise.
  arXiv  Detail & Related papers  (2020-05-27T08:30:15Z)
• Learning nonlinear dynamical systems from a single trajectory [102.60042167341956]
  We introduce algorithms for learning nonlinear dynamical systems of the form $x_t+1=sigma(Thetastarx_t)+varepsilon_t$. We give an algorithm that recovers the weight matrix $Thetastar$ from a single trajectory with optimal sample complexity and linear running time.
  arXiv  Detail & Related papers  (2020-04-30T10:42:48Z)
• Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems [34.394552166070746]
  We study gradient based algorithms to learn the system dynamics $theta$ from samples obtained from a single finite trajectory. Unlike existing work, our bounds are noise sensitive which allows for learning ground-truth dynamics with high accuracy and small sample complexity.
  arXiv  Detail & Related papers  (2020-02-20T02:36:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.