Active Learning for Nonlinear System Identification with Guarantees

Authors: Horia Mania, Michael I. Jordan, Benjamin Recht

JMLR 2022 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We show that our method estimates nonlinear dynamical systems at a parametric rate, similar to the statistical rate of standard linear regression. Keywords: nonlinear dynamical systems, system identification, least squares, control theory. We quantify the data requirements of identifying A, leaving computational considerations for future work.
Researcher Affiliation Academia Horia Mania EMAIL Michael I. Jordan EMAIL Benjamin Recht EMAIL Department of Electrical Engineering and Computer Science University of California Berkeley, CA 94720-1776, USA
Pseudocode Yes Our method for estimating the parameters of a dynamical system (1) is shown in Algorithm 1. The trajectory planning and tracking routines are discussed in detail in Sections 3.1 and 3.2, respectively. Our method is also presented in one block of pseudo-code in Appendix E. We now state our main result. [...] Appendix E. Detailed Pseudo-code of Algorithm 1
Open Source Code No The paper does not explicitly state that source code for the described methodology is being released or provide a link to a repository. While it is under a CC-BY 4.0 license, this pertains to the paper itself, not an explicit code release.
Open Datasets No The paper uses illustrative examples (Example 1, Example 2: Smoothed Piecewise Linear System, Example 3: Simple Pendulum) to demonstrate theoretical concepts and assumptions, rather than conducting empirical experiments on specific datasets. No publicly available datasets with access information are provided.
Dataset Splits No The paper does not conduct empirical experiments using datasets, therefore, no training/test/validation dataset splits are provided.
Hardware Specification No The paper is theoretical and does not describe empirical experiments. Consequently, no hardware specifications for running experiments are mentioned.
Software Dependencies No The paper is theoretical and does not describe empirical experiments. Therefore, no specific software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and focuses on algorithm design and proofs. It does not include an experimental section detailing hyperparameters, training configurations, or system-level settings.