ICML 2024poster1 citations
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
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.
BibTeX
@inproceedings{
eringis2024pacbayesian,
title={{PAC}-Bayesian Error Bound, via R\'enyi Divergence, for a Class of Linear Time-Invariant State-Space Models},
author={Deividas Eringis and john leth and Zheng-Hua Tan and Rafal Wisniewski and Mihaly Petreczky},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=a1Olc2QhPv}
}