Joint Learning of Linear Time-Invariant Dynamical Systems
- URL: http://arxiv.org/abs/2112.10955v6
- Date: Tue, 2 Jan 2024 13:40:50 GMT
- Title: Joint Learning of Linear Time-Invariant Dynamical Systems
- Authors: Aditya Modi, Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George
Michailidis
- Abstract summary: This paper investigates methods for jointly estimating the transition matrices of multiple systems.
We establish finite-time estimation error rates that fully reflect the roles of trajectory lengths, dimension, and number of systems under consideration.
We develop novel techniques that are of interest for addressing similar joint-learning problems.
- Score: 31.879189478584095
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Linear time-invariant systems are very popular models in system theory and
applications. A fundamental problem in system identification that remains
rather unaddressed in extant literature is to leverage commonalities amongst
related linear systems to estimate their transition matrices more accurately.
To address this problem, the current paper investigates methods for jointly
estimating the transition matrices of multiple systems. It is assumed that the
transition matrices are unknown linear functions of some unknown shared basis
matrices. We establish finite-time estimation error rates that fully reflect
the roles of trajectory lengths, dimension, and number of systems under
consideration. The presented results are fairly general and show the
significant gains that can be achieved by pooling data across systems in
comparison to learning each system individually. Further, they are shown to be
robust against model misspecifications. To obtain the results, we develop novel
techniques that are of interest for addressing similar joint-learning problems.
They include tightly bounding estimation errors in terms of the
eigen-structures of transition matrices, establishing sharp high probability
bounds for singular values of dependent random matrices, and capturing effects
of misspecified transition matrices as the systems evolve over time.
Related papers
- Learning Linear Dynamics from Bilinear Observations [8.238163867581848]
We consider the problem of learning a realization of a partially observed dynamical system with linear state transitions and bilinear observations.
Under very mild assumptions on the process and measurement noises, we provide a finite time analysis for learning the unknown dynamics matrices.
arXiv Detail & Related papers (2024-09-24T23:11:47Z) - Exponential time differencing for matrix-valued dynamical systems [0.0]
Exponential time differencing (ETD) is known to produce highly stable numerical schemes by treating the linear term in an exact fashion.
We propose an extension of the class of ETD algorithms to matrix-valued dynamical equations.
This allows us to produce highly efficient and stable integration schemes.
arXiv Detail & Related papers (2024-06-19T18:22:23Z) - Identifying Systems with Symmetries using Equivariant Autoregressive
Reservoir Computers [0.0]
Investigation focuses on identifying systems with symmetries using equivariant autoregressive reservoir computers.
General results in structured matrix approximation theory are presented, exploring a two-fold approach.
arXiv Detail & Related papers (2023-11-16T02:32:26Z) - 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) - Causality-Based Multivariate Time Series Anomaly Detection [63.799474860969156]
We formulate the anomaly detection problem from a causal perspective and view anomalies as instances that do not follow the regular causal mechanism to generate the multivariate data.
We then propose a causality-based anomaly detection approach, which first learns the causal structure from data and then infers whether an instance is an anomaly relative to the local causal mechanism.
We evaluate our approach with both simulated and public datasets as well as a case study on real-world AIOps applications.
arXiv Detail & Related papers (2022-06-30T06:00:13Z) - Supervised DKRC with Images for Offline System Identification [77.34726150561087]
Modern dynamical systems are becoming increasingly non-linear and complex.
There is a need for a framework to model these systems in a compact and comprehensive representation for prediction and control.
Our approach learns these basis functions using a supervised learning approach.
arXiv Detail & Related papers (2021-09-06T04:39:06Z) - High-dimensional separability for one- and few-shot learning [58.8599521537]
This work is driven by a practical question, corrections of Artificial Intelligence (AI) errors.
Special external devices, correctors, are developed. They should provide quick and non-iterative system fix without modification of a legacy AI system.
New multi-correctors of AI systems are presented and illustrated with examples of predicting errors and learning new classes of objects by a deep convolutional neural network.
arXiv Detail & Related papers (2021-06-28T14:58:14Z) - Linear embedding of nonlinear dynamical systems and prospects for
efficient quantum algorithms [74.17312533172291]
We describe a method for mapping any finite nonlinear dynamical system to an infinite linear dynamical system (embedding)
We then explore an approach for approximating the resulting infinite linear system with finite linear systems (truncation)
arXiv Detail & Related papers (2020-12-12T00:01:10Z) - Learning Partially Observed Linear Dynamical Systems from Logarithmic
Number of Samples [4.7464518249313805]
We study the problem of learning partially observed linear dynamical systems from a single sample trajectory.
Our result significantly improves the sample complexity of learning partially observed linear dynamical systems.
arXiv Detail & Related papers (2020-10-08T14:23:48Z) - 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)
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.