Salvato in:
Dettagli Bibliografici
Autori principali: Bharadwaj, Shreyas, Mishra, Bamdev, Mostajeran, Cyrus, Padoan, Alberto, Coulson, Jeremy, Banavar, Ravi N.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2511.09242
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908994680913920
author Bharadwaj, Shreyas
Mishra, Bamdev
Mostajeran, Cyrus
Padoan, Alberto
Coulson, Jeremy
Banavar, Ravi N.
author_facet Bharadwaj, Shreyas
Mishra, Bamdev
Mostajeran, Cyrus
Padoan, Alberto
Coulson, Jeremy
Banavar, Ravi N.
contents The paper studies a geometrically robust least-squares problem that extends classical and norm-based robust formulations. Rather than minimizing residual error for fixed or perturbed data, we interpret least-squares as enforcing approximate subspace inclusion between measured and true data spaces. The uncertainty in this geometric relation is modeled as a metric ball on the Grassmannian manifold, leading to a min-max problem over Euclidean and manifold variables. The inner maximization admits a closed-form solution, enabling an efficient algorithm with a transparent geometric interpretation. Applied to robust finite-horizon linear-quadratic tracking in data-enabled predictive control, the method improves upon existing robust least-squares formulations, achieving stronger robustness and favorable scaling under small uncertainty.
format Preprint
id arxiv_https___arxiv_org_abs_2511_09242
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Least-Squares Optimization for Data-Driven Predictive Control: A Geometric Approach
Bharadwaj, Shreyas
Mishra, Bamdev
Mostajeran, Cyrus
Padoan, Alberto
Coulson, Jeremy
Banavar, Ravi N.
Optimization and Control
Machine Learning
The paper studies a geometrically robust least-squares problem that extends classical and norm-based robust formulations. Rather than minimizing residual error for fixed or perturbed data, we interpret least-squares as enforcing approximate subspace inclusion between measured and true data spaces. The uncertainty in this geometric relation is modeled as a metric ball on the Grassmannian manifold, leading to a min-max problem over Euclidean and manifold variables. The inner maximization admits a closed-form solution, enabling an efficient algorithm with a transparent geometric interpretation. Applied to robust finite-horizon linear-quadratic tracking in data-enabled predictive control, the method improves upon existing robust least-squares formulations, achieving stronger robustness and favorable scaling under small uncertainty.
title Robust Least-Squares Optimization for Data-Driven Predictive Control: A Geometric Approach
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2511.09242