Asymptotics of predictive stochastic complexity
[For the entire collection see Zbl 0761.00004.] From the authors' abstract: The purpose of this expository paper is to give a survey of rigorous asymptotic results in the theory of stochastic complexity. A brief survey of the early developments and the ideas that culminated in a basic inequality of universal codes are provided. Results are presented, which show that the lower bound given by the basic inequality is achieved in many cases. The asymptotic behaviour of different kinds of predictive stochastic complexities associated with ARMA processes are established. Finally, extensions of the ARMA results to multivariable systems, to Ljung's scheme, and to nonparametric problems are considered.
- scientific article; zbMATH DE number 4200119
- Predictive stochastic complexity and model estimation for finite-state processes
- scientific article; zbMATH DE number 3971958
- On stochastic complexity estimation: a decision-theoretic approach
- Predictive complexity and generalized entropy rate of stationary ergodic processes
- Stochastic complexity in learning
- scientific article; zbMATH DE number 4068049
- Towards a predictive computational complexity theory
- Stochastic complexity and modeling
- Predictive stochastic complexity and model estimation for finite-state processes
- On Rissanen's predictive stochastic complexity for stationary ARMA processes
- A tight upper bound on Kolmogorov complexity and uniformly optimal prediction
- scientific article; zbMATH DE number 4200119 (Why is no real title available?)
- AR( infinity ) estimation and nonparametric stochastic complexity
- Algorithmic Learning Theory
- Algorithmic complexity bounds on future prediction errors
This page was built for publication: Asymptotics of predictive stochastic complexity
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4694334)
