PAC-Bayesian theory for stochastic LTI systems

Deividas Eringis (1) , John Leth (1) , Zheng-Hua Tan (1) , Rafal Wisniewski (1) , Alireza Fakhrizadeh Esfahani (2) , Mihaly Petreczky (2)

1 AAU - Aalborg University [Denmark]
2 CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189

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, PAC-Bayesian error bounds are known to be useful for analyzing machine learning algorithms and for deriving new ones.

Domaines: Apprentissage [cs.LG]

Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Alireza Fakhrizadeh Esfahani, et al.. PAC-Bayesian theory for stochastic LTI systems. IEEE Conference on Decision and Control, Dec 2021, Austin, United States. ⟨hal-03331763⟩