Abstract
We consider the problem of learning linear dynamical systems under adversarial contamination from a single trajectory of length $T$. While identification of linear dynamical systems itself is well-studied, the problem of robust system identification under adversarial contamination is relatively less explored. In this work, we study the setting where a fraction of the $T$ observations are contaminated by adversarial outliers. We propose different estimators based on relaxations of least-trimmed squares along with an alternating minimization algorithm. Furthermore, we also propose two estimators which exploit the group-sparsity (through penalization/hard-constraints) of the outliers. For the estimator with group-sparse penalty, we derive non-asymptotic error bounds which establish its robustness to outliers. We also show empirically that the proposed estimators work well in practice.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Ruwanpathirana, A. K., & Tyagi, H. (2026). RobustLDS: Learning linear dynamical systems under adversarial corruptions. https://omanscience.com/en/articles/robustlds-learning-linear-dynamical-systems-under-adversarial-corruptions
MLA 9
Ruwanpathirana, Aravinda Kanchana, and Hemant Tyagi. "RobustLDS: Learning linear dynamical systems under adversarial corruptions." https://omanscience.com/en/articles/robustlds-learning-linear-dynamical-systems-under-adversarial-corruptions.
Chicago (author–date)
Ruwanpathirana, Aravinda Kanchana, and Hemant Tyagi. 2026. "RobustLDS: Learning linear dynamical systems under adversarial corruptions." https://omanscience.com/en/articles/robustlds-learning-linear-dynamical-systems-under-adversarial-corruptions.
Harvard
Ruwanpathirana, A. K. and Tyagi, H. (2026) 'RobustLDS: Learning linear dynamical systems under adversarial corruptions', Available at: https://omanscience.com/en/articles/robustlds-learning-linear-dynamical-systems-under-adversarial-corruptions.
Vancouver
Ruwanpathirana AK, Tyagi H. RobustLDS: Learning linear dynamical systems under adversarial corruptions. https://omanscience.com/en/articles/robustlds-learning-linear-dynamical-systems-under-adversarial-corruptions
IEEE
A. K. Ruwanpathirana, and H. Tyagi, "RobustLDS: Learning linear dynamical systems under adversarial corruptions," https://omanscience.com/en/articles/robustlds-learning-linear-dynamical-systems-under-adversarial-corruptions.