Saved in:
Bibliographic Details
Main Authors: Raghavan, Aneesh, Johansson, Karl Henrik
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.15687
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917621034647552
author Raghavan, Aneesh
Johansson, Karl Henrik
author_facet Raghavan, Aneesh
Johansson, Karl Henrik
contents A given region in 2-D Euclidean space is divided by a unknown linear classifier in to two sets each carrying a label. The objective of an agent with known dynamics traversing the region is to identify the true classifier while paying a control cost across its trajectory. We consider two scenarios: (i) the agent is able to measure the true label perfectly; (ii) the observed label is the true label multiplied by noise. We present the following: (i) the classifier identification problem formulated as a control problem; (ii) geometric interpretation of the control problem resulting in one step modified control problems; (iii) control algorithms that result in data sets which are used to identify the true classifier with accuracy; (iv) convergence of estimated classifier to the true classifier when the observed label is not corrupted by noise; (iv) numerical example demonstrating the utility of the control algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15687
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Motion Planning for Identification of Linear Classifiers
Raghavan, Aneesh
Johansson, Karl Henrik
Systems and Control
A given region in 2-D Euclidean space is divided by a unknown linear classifier in to two sets each carrying a label. The objective of an agent with known dynamics traversing the region is to identify the true classifier while paying a control cost across its trajectory. We consider two scenarios: (i) the agent is able to measure the true label perfectly; (ii) the observed label is the true label multiplied by noise. We present the following: (i) the classifier identification problem formulated as a control problem; (ii) geometric interpretation of the control problem resulting in one step modified control problems; (iii) control algorithms that result in data sets which are used to identify the true classifier with accuracy; (iv) convergence of estimated classifier to the true classifier when the observed label is not corrupted by noise; (iv) numerical example demonstrating the utility of the control algorithms.
title Motion Planning for Identification of Linear Classifiers
topic Systems and Control
url https://arxiv.org/abs/2403.15687