PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise
The bound derived relates the expectation of prediction errors with the prediction error generated by the model on the data used for learning to provide finite-sample error bounds for the prediction error and parameter estimation error for a wide class of system identification algorithms.
M. Petreczky, Mohamad Al Ahdab, John Leth
· 0 citations