A median-of-bucket-OLS algorithm recovers sub-Gaussian-style system identification rates under heavy-tailed noise with only finite fourth moment, and tolerates a small fraction of adversarially corrupted trajectories.
Robust multivariat e mean estimation: the optimality of trimmed mean
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SY 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Outlier-Robust Linear System Identification Under Heavy-tailed Noise
A median-of-bucket-OLS algorithm recovers sub-Gaussian-style system identification rates under heavy-tailed noise with only finite fourth moment, and tolerates a small fraction of adversarially corrupted trajectories.