A deterministic multi-trajectory probing scheme plus ridge regression learns the linearization of a noisy nonlinear system, achieving O(N^{-1/4}) worst-case error from N experiments under initialization constraints.
Safely learning dynamical systems from short trajectories
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Linearized Models from Nonlinear Systems under Initialization Constraints with Finite Data
A deterministic multi-trajectory probing scheme plus ridge regression learns the linearization of a noisy nonlinear system, achieving O(N^{-1/4}) worst-case error from N experiments under initialization constraints.