PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models

2022-12-30 · Deividas Eringis, John Leth, Zheng-Hua Tan, Rafal Wisniewski, Mihaly Petreczky

In this paper we derive a PAC-Bayesian-Like 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-Like error bound for such systems, 3) discuss various consequences of this error bound.

📄 PDF Abstract BibTeX arXiv:2212.14838

Code (0)

등록된 구현이 없습니다.

Tasks

EconometricsState Space Models

Improved PAC-Bayesian Bounds for Linear Regression

2019-12-06 · Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain, Mihaly Petreczky

In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. [10]. The improvements are twofold. First, the proposed error bound is tighter, and converges to the generalization l…

regression Time Series Time Series Analysis

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

2023-03-29 · Deividas Eringis, John Leth, Zheng-Hua Tan, Rafael Wisniewski 외

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 u…

Non-Vacuous Generalisation Bounds for Shallow Neural Networks

2022-02-03 · Felix Biggs, Benjamin Guedj

We focus on a specific class of shallow neural networks with a single hidden layer, namely those with $L_2$-normalised data and either a sigmoid-shaped Gaussian error function ("erf") activation or a Gaussian Error Linea…

PAC-Bayesian Theory Meets Bayesian Inference

2016-05-27 · NeurIPS 2016 12 · Pascal Germain, Francis Bach, Alexandre Lacoste, Simon Lacoste-Julien

We exhibit a strong link between frequentist PAC-Bayesian risk bounds and the Bayesian marginal likelihood. That is, for the negative log-likelihood loss function, we show that the minimization of PAC-Bayesian generaliza…

Bayesian Inference regression

Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits

2024-06-20 · Ziyi Huang, Henry Lam, Haofeng Zhang

Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. Despite the superior practical performance, their theoretical justification is less investigated in the lit…

Bayesian Inference Thompson Sampling