RobustLDS: Learning linear dynamical systems under adversarial corruptions
The work proposes estimators for learning linear dynamical systems when a fraction of observations are corrupted by an adversary. It introduces methods based on relaxing least-trimmed squares and alternating minimization, along with estimators exploiting group-sparsity of outliers. The results provide non-asymptotic error bounds proving the robustness of these methods under adversarial contamination from a single trajectory.