Back to Search Start Over

PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss

Authors :
Eringis, Deividas
Leth, John
Tan, Zheng-Hua
Wisniewski, Rafael
Petreczky, Mihaly
Publication Year :
2023

Abstract

In this paper we derive a Probably Approxilmately Correct(PAC)-Bayesian error bound for linear time-invariant (LTI) stochastic dynamical systems with inputs. Such bounds are widespread in machine learning, and they are useful for characterizing the predictive power of models learned from finitely many data points. In particular, with the bound derived in this paper relates future average prediction errors with the prediction error generated by the model on the data used for learning. In turn, this allows us to provide finite-sample error bounds for a wide class of learning/system identification algorithms. Furthermore, as LTI systems are a sub-class of recurrent neural networks (RNNs), these error bounds could be a first step towards PAC-Bayesian bounds for RNNs.<br />Comment: arXiv admin note: text overlap with arXiv:2212.14838

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2303.16816
Document Type :
Working Paper