Skip to yearly menu bar Skip to main content


Poster

PAC-Bayesian Error Bound, via Rényi Divergence, for a Class of Linear Time-Invariant State-Space Models

Deividas Eringis · john leth · Zheng-Hua Tan · Rafal Wisniewski · Mihaly Petreczky

Hall C 4-9 #908
[ ] [ Paper PDF ]
[ Slides [ Poster
Thu 25 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

In this paper we derive a PAC-Bayesian error bound for a class of stochastic dynamical systems with inputs, namely, for linear time-invariant stochastic state-space models (stochastic LTI systems for short). This class of systems is widely used in control engineering and econometrics, in particular, they represent a special case of recurrent neural networks. In this paper we 1) formalize the learning problem for stochastic LTI systems with inputs, 2) derive a PAC-Bayesian error bound for such systems, and 3) discuss various consequences of this error bound.

Chat is not available.