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

Deividas Eringis, John Leth, Zheng-Hua Tan, Rafael Wisniewski, Mihaly Petreczky
3/29/2023
stat.MLcs.LG

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A finite-sample generalization bound for stable LPV systems

81% match2024

Improving Generalization of Complex Models under Unbounded Loss Using PAC-Bayes Bounds

81% match2023

Bayesian Modeling and Estimation of Linear Time-Variant Systems using Neural Networks and Gaussian Processes

79% match2025

Research Program: Theory of Learning in Dynamical Systems

79% match2025

Better-than-KL PAC-Bayes Bounds

79% match2024

Classification Error Bound for Low Bayes Error Conditions in Machine Learning

79% match2025

Cite this paper

@article{eringis2023pacbayesian,
  title  = {PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss},
  author = {Deividas Eringis and John Leth and Zheng-Hua Tan and Rafael Wisniewski and Mihaly Petreczky},
  year   = {2023},
  eprint = {2303.16816},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.16816v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.16816.svg)](https://codeofpaper.com/paper/2303.16816)

Discussion