PAC-Bayesian theory for stochastic LTI systems
This work addresses the problem of analyzing and deriving machine learning algorithms, particularly for dynamical systems, but it is incremental as it extends existing PAC-Bayesian theory to a specific model type.
The paper derived a PAC-Bayesian error bound for autonomous stochastic LTI state-space models, aiming to enable similar bounds for more general dynamical systems like recurrent neural networks.
In this paper we derive a PAC-Bayesian error bound for autonomous stochastic LTI state-space models. The motivation for deriving such error bounds is that they will allow deriving similar error bounds for more general dynamical systems, including recurrent neural networks. In turn, PACBayesian error bounds are known to be useful for analyzing machine learning algorithms and for deriving new ones.